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

Dataset: Open Web Text

Neuron 1929 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: 3.0439. Min Range: -3.0439

Max Act: 3.0439. Min Act: -0.1700

Data Index: 3636524 (Open Web Text)

Max Activating Token Index: 682

Text #1

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.9310. Min Act: -0.1700

Data Index: 8103380 (Open Web Text)

Max Activating Token Index: 661

Text #2

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.9376. Min Act: -0.1700

Data Index: 8011941 (Open Web Text)

Max Activating Token Index: 545

Text #3

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.9016. Min Act: -0.1700

Data Index: 2917182 (Open Web Text)

Max Activating Token Index: 511

Text #4

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8932. Min Act: -0.1700

Data Index: 3537292 (Open Web Text)

Max Activating Token Index: 588

Text #5

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8670. Min Act: -0.1700

Data Index: 1098680 (Open Web Text)

Max Activating Token Index: 628

Text #6

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8695. Min Act: -0.1700

Data Index: 1574198 (Open Web Text)

Max Activating Token Index: 357

Text #7

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8435. Min Act: -0.1700

Data Index: 7022351 (Open Web Text)

Max Activating Token Index: 228

Text #8

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8491. Min Act: -0.1700

Data Index: 6714004 (Open Web Text)

Max Activating Token Index: 493

Text #9

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8226. Min Act: -0.1700

Data Index: 2619638 (Open Web Text)

Max Activating Token Index: 396

Text #10

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8173. Min Act: -0.1700

Data Index: 651173 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8118. Min Act: -0.1700

Data Index: 6170022 (Open Web Text)

Max Activating Token Index: 834

Text #12

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8196. Min Act: -0.1700

Data Index: 4032729 (Open Web Text)

Max Activating Token Index: 301

Text #13

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8063. Min Act: -0.1700

Data Index: 6203216 (Open Web Text)

Max Activating Token Index: 882

Text #14

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.7927. Min Act: -0.1700

Data Index: 5424376 (Open Web Text)

Max Activating Token Index: 796

Text #15

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.8097. Min Act: -0.1700

Data Index: 1967257 (Open Web Text)

Max Activating Token Index: 817

Text #16

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.7779. Min Act: -0.1700

Data Index: 2537555 (Open Web Text)

Max Activating Token Index: 353

Text #17

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.7901. Min Act: -0.1700

Data Index: 6265356 (Open Web Text)

Max Activating Token Index: 840

Text #18

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.7790. Min Act: -0.1700

Data Index: 6423394 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 3.0439. Min Range: -3.0439

Max Act: 2.7604. Min Act: -0.1700

Data Index: 4713650 (Open Web Text)

Max Activating Token Index: 370