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

Dataset: Open Web Text

Neuron 514 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: 3.3899. Min Range: -3.3899

Max Act: 3.3899. Min Act: -0.1700

Data Index: 4957777 (Open Web Text)

Max Activating Token Index: 780

Text #1

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.3162. Min Act: -0.1700

Data Index: 6362475 (Open Web Text)

Max Activating Token Index: 506

Text #2

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.3115. Min Act: -0.1700

Data Index: 6823137 (Open Web Text)

Max Activating Token Index: 646

Text #3

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.3270. Min Act: -0.1700

Data Index: 3330933 (Open Web Text)

Max Activating Token Index: 431

Text #4

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2607. Min Act: -0.1700

Data Index: 8011832 (Open Web Text)

Max Activating Token Index: 600

Text #5

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2670. Min Act: -0.1700

Data Index: 1160781 (Open Web Text)

Max Activating Token Index: 793

Text #6

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2587. Min Act: -0.1700

Data Index: 1287654 (Open Web Text)

Max Activating Token Index: 428

Text #7

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2823. Min Act: -0.1700

Data Index: 4759643 (Open Web Text)

Max Activating Token Index: 535

Text #8

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2893. Min Act: -0.1700

Data Index: 7754998 (Open Web Text)

Max Activating Token Index: 445

Text #9

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2626. Min Act: -0.1700

Data Index: 4951631 (Open Web Text)

Max Activating Token Index: 753

Text #10

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2613. Min Act: -0.1700

Data Index: 4790923 (Open Web Text)

Max Activating Token Index: 38

Text #11

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2084. Min Act: -0.1700

Data Index: 4417944 (Open Web Text)

Max Activating Token Index: 476

Text #12

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2460. Min Act: -0.1700

Data Index: 4841651 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2462. Min Act: -0.1700

Data Index: 3480874 (Open Web Text)

Max Activating Token Index: 659

Text #14

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2531. Min Act: -0.1700

Data Index: 2152901 (Open Web Text)

Max Activating Token Index: 528

Text #15

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2275. Min Act: -0.1700

Data Index: 6502453 (Open Web Text)

Max Activating Token Index: 156

Text #16

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2478. Min Act: -0.1700

Data Index: 2704249 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2191. Min Act: -0.1700

Data Index: 2124512 (Open Web Text)

Max Activating Token Index: 219

Text #18

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2038. Min Act: -0.1700

Data Index: 288383 (Open Web Text)

Max Activating Token Index: 418

Text #19

Max Range: 3.3899. Min Range: -3.3899

Max Act: 3.2166. Min Act: -0.1700

Data Index: 2730546 (Open Web Text)

Max Activating Token Index: 177