< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 780 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.6367. Min Act: -0.1700

Data Index: 612372 (Open Web Text)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.6134. Min Act: -0.1700

Data Index: 2564720 (Open Web Text)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.6015. Min Act: -0.1700

Data Index: 7124270 (Open Web Text)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5618. Min Act: -0.1700

Data Index: 6371417 (Open Web Text)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5777. Min Act: -0.1700

Data Index: 7528799 (Open Web Text)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5903. Min Act: -0.1700

Data Index: 3387909 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5556. Min Act: -0.1700

Data Index: 2833153 (Open Web Text)

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5626. Min Act: -0.1700

Data Index: 666747 (Open Web Text)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5371. Min Act: -0.1700

Data Index: 6540081 (Open Web Text)

Max Activating Token Index: 429

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5176. Min Act: -0.1700

Data Index: 5792514 (Open Web Text)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5032. Min Act: -0.1700

Data Index: 2646982 (Open Web Text)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5023. Min Act: -0.1700

Data Index: 5660953 (Open Web Text)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5129. Min Act: -0.1700

Data Index: 8042231 (Open Web Text)

Max Activating Token Index: 729

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.4935. Min Act: -0.1700

Data Index: 6236537 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5044. Min Act: -0.1700

Data Index: 1074764 (Open Web Text)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.4940. Min Act: -0.1700

Data Index: 571964 (Open Web Text)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.4907. Min Act: -0.1700

Data Index: 8105312 (Open Web Text)

Max Activating Token Index: 406

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.4881. Min Act: -0.1700

Data Index: 8143677 (Open Web Text)

Max Activating Token Index: 430

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.5150. Min Act: -0.1700

Data Index: 6626542 (Open Web Text)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6367. Min Range: -2.6367

Max Act: 2.4756. Min Act: -0.1700

Data Index: 8284047 (Open Web Text)

Max Activating Token Index: 734

Click toggle to see full text

Truncated

Full Text #19