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

Dataset: Open Web Text

Neuron 1235 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: 4.5457. Min Range: -4.5457

Max Act: 4.5457. Min Act: -0.1700

Data Index: 5899607 (Open Web Text)

Max Activating Token Index: 808

Text #1

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.4525. Min Act: -0.1700

Data Index: 8158286 (Open Web Text)

Max Activating Token Index: 693

Text #2

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.3511. Min Act: -0.1700

Data Index: 5650498 (Open Web Text)

Max Activating Token Index: 691

Text #3

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.3230. Min Act: -0.1700

Data Index: 4469108 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.3315. Min Act: -0.1700

Data Index: 5812338 (Open Web Text)

Max Activating Token Index: 207

Text #5

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.3167. Min Act: -0.1700

Data Index: 2063763 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2584. Min Act: -0.1700

Data Index: 934354 (Open Web Text)

Max Activating Token Index: 525

Text #7

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2418. Min Act: -0.1700

Data Index: 2477995 (Open Web Text)

Max Activating Token Index: 838

Text #8

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2356. Min Act: -0.1700

Data Index: 774731 (Open Web Text)

Max Activating Token Index: 436

Text #9

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2587. Min Act: -0.1700

Data Index: 2197086 (Open Web Text)

Max Activating Token Index: 399

Text #10

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2455. Min Act: -0.1700

Data Index: 1766249 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2882. Min Act: -0.1700

Data Index: 6632399 (Open Web Text)

Max Activating Token Index: 590

Text #12

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2367. Min Act: -0.1700

Data Index: 6960066 (Open Web Text)

Max Activating Token Index: 204

Text #13

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.1927. Min Act: -0.1700

Data Index: 4864143 (Open Web Text)

Max Activating Token Index: 196

Text #14

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2020. Min Act: -0.1700

Data Index: 1122364 (Open Web Text)

Max Activating Token Index: 457

Text #15

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.1834. Min Act: -0.1700

Data Index: 3796529 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.1955. Min Act: -0.1700

Data Index: 8355562 (Open Web Text)

Max Activating Token Index: 347

Text #17

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.2041. Min Act: -0.1700

Data Index: 1613186 (Open Web Text)

Max Activating Token Index: 677

Text #18

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.1793. Min Act: -0.1700

Data Index: 6254219 (Open Web Text)

Max Activating Token Index: 587

Text #19

Max Range: 4.5457. Min Range: -4.5457

Max Act: 4.1877. Min Act: -0.1700

Data Index: 720014 (Open Web Text)

Max Activating Token Index: 556