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

Dataset: Open Web Text

Neuron 1165 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: 4.3459. Min Range: -4.3459

Max Act: 4.3459. Min Act: -0.1700

Data Index: 3623780 (Open Web Text)

Max Activating Token Index: 845

Text #1

Max Range: 4.3459. Min Range: -4.3459

Max Act: 4.0359. Min Act: -0.1700

Data Index: 3389236 (Open Web Text)

Max Activating Token Index: 345

Text #2

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.9959. Min Act: -0.1700

Data Index: 125729 (Open Web Text)

Max Activating Token Index: 919

Text #3

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.9725. Min Act: -0.1700

Data Index: 6991571 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.9021. Min Act: -0.1700

Data Index: 7709475 (Open Web Text)

Max Activating Token Index: 290

Text #5

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.9135. Min Act: -0.1700

Data Index: 416050 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7981. Min Act: -0.1700

Data Index: 1963978 (Open Web Text)

Max Activating Token Index: 792

Text #7

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.8015. Min Act: -0.1700

Data Index: 691120 (Open Web Text)

Max Activating Token Index: 960

Text #8

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.8161. Min Act: -0.1700

Data Index: 4136737 (Open Web Text)

Max Activating Token Index: 209

Text #9

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7568. Min Act: -0.1700

Data Index: 6932579 (Open Web Text)

Max Activating Token Index: 845

Text #10

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7950. Min Act: -0.1700

Data Index: 284455 (Open Web Text)

Max Activating Token Index: 231

Text #11

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.8192. Min Act: -0.1700

Data Index: 6959761 (Open Web Text)

Max Activating Token Index: 505

Text #12

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7618. Min Act: -0.1700

Data Index: 3274755 (Open Web Text)

Max Activating Token Index: 174

Text #13

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7307. Min Act: -0.1700

Data Index: 7416183 (Open Web Text)

Max Activating Token Index: 648

Text #14

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7193. Min Act: -0.1700

Data Index: 2361698 (Open Web Text)

Max Activating Token Index: 440

Text #15

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7142. Min Act: -0.1700

Data Index: 2662621 (Open Web Text)

Max Activating Token Index: 326

Text #16

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7371. Min Act: -0.1700

Data Index: 8068396 (Open Web Text)

Max Activating Token Index: 205

Text #17

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.6857. Min Act: -0.1700

Data Index: 6749036 (Open Web Text)

Max Activating Token Index: 511

Text #18

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7352. Min Act: -0.1700

Data Index: 6059707 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 4.3459. Min Range: -4.3459

Max Act: 3.7276. Min Act: -0.1700

Data Index: 6993981 (Open Web Text)

Max Activating Token Index: 595