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

Dataset: Open Web Text

Neuron 2948 in Layer 4

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: 4.2064. Min Range: -4.2064

Max Act: 4.2064. Min Act: -0.1700

Data Index: 6608760 (Open Web Text)

Max Activating Token Index: 50

Text #1

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.1459. Min Act: -0.1700

Data Index: 2349724 (Open Web Text)

Max Activating Token Index: 151

Text #2

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.1441. Min Act: -0.1700

Data Index: 30757 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.1262. Min Act: -0.1700

Data Index: 2878230 (Open Web Text)

Max Activating Token Index: 989

Text #4

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0596. Min Act: -0.1700

Data Index: 215959 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0512. Min Act: -0.1700

Data Index: 6608756 (Open Web Text)

Max Activating Token Index: 91

Text #6

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0160. Min Act: -0.1700

Data Index: 7304369 (Open Web Text)

Max Activating Token Index: 925

Text #7

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0394. Min Act: -0.1700

Data Index: 3458991 (Open Web Text)

Max Activating Token Index: 30

Text #8

Max Range: 4.2064. Min Range: -4.2064

Max Act: 4.0080. Min Act: -0.1700

Data Index: 4418878 (Open Web Text)

Max Activating Token Index: 677

Text #9

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9777. Min Act: -0.1700

Data Index: 8108190 (Open Web Text)

Max Activating Token Index: 564

Text #10

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9652. Min Act: -0.1700

Data Index: 2749078 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9925. Min Act: -0.1700

Data Index: 1362426 (Open Web Text)

Max Activating Token Index: 569

Text #12

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9774. Min Act: -0.1700

Data Index: 766411 (Open Web Text)

Max Activating Token Index: 529

Text #13

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9691. Min Act: -0.1700

Data Index: 5915380 (Open Web Text)

Max Activating Token Index: 48

Text #14

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9977. Min Act: -0.1700

Data Index: 7379970 (Open Web Text)

Max Activating Token Index: 967

Text #15

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9403. Min Act: -0.1700

Data Index: 1122901 (Open Web Text)

Max Activating Token Index: 7

Text #16

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9539. Min Act: -0.1700

Data Index: 2572858 (Open Web Text)

Max Activating Token Index: 229

Text #17

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9637. Min Act: -0.1700

Data Index: 1245171 (Open Web Text)

Max Activating Token Index: 754

Text #18

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9396. Min Act: -0.1700

Data Index: 7283205 (Open Web Text)

Max Activating Token Index: 503

Text #19

Max Range: 4.2064. Min Range: -4.2064

Max Act: 3.9614. Min Act: -0.1700

Data Index: 2632642 (Open Web Text)

Max Activating Token Index: 35