< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 2083 in Layer 3

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: 2.6787. Min Range: -2.6787

Max Act: 2.6787. Min Act: -0.1700

Data Index: 31312 (Open Web Text)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.6767. Min Act: -0.1700

Data Index: 2142884 (Open Web Text)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.6385. Min Act: -0.1700

Data Index: 3720682 (Open Web Text)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.6163. Min Act: -0.1700

Data Index: 6259651 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.6127. Min Act: -0.1700

Data Index: 3218194 (Open Web Text)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5864. Min Act: -0.1700

Data Index: 2743675 (Open Web Text)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5762. Min Act: -0.1700

Data Index: 473227 (Open Web Text)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5916. Min Act: -0.1700

Data Index: 4543530 (Open Web Text)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5523. Min Act: -0.1700

Data Index: 972949 (Open Web Text)

Max Activating Token Index: 732

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5498. Min Act: -0.1700

Data Index: 860317 (Open Web Text)

Max Activating Token Index: 380

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5357. Min Act: -0.1700

Data Index: 3426756 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5390. Min Act: -0.1700

Data Index: 7389603 (Open Web Text)

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5003. Min Act: -0.1700

Data Index: 2080990 (Open Web Text)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5548. Min Act: -0.1700

Data Index: 254792 (Open Web Text)

Max Activating Token Index: 467

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5181. Min Act: -0.1700

Data Index: 1028215 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5405. Min Act: -0.1700

Data Index: 31311 (Open Web Text)

Max Activating Token Index: 973

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5181. Min Act: -0.1700

Data Index: 3582634 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.4711. Min Act: -0.1700

Data Index: 3549361 (Open Web Text)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5181. Min Act: -0.1700

Data Index: 1978755 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6787. Min Range: -2.6787

Max Act: 2.5181. Min Act: -0.1700

Data Index: 1287283 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19