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

Dataset: Open Web Text

Neuron 241 in Layer 6

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: 5.8268. Min Range: -5.8268

Max Act: 5.8268. Min Act: -0.1700

Data Index: 452889 (Open Web Text)

Max Activating Token Index: 975

Text #1

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.8099. Min Act: -0.1700

Data Index: 7669552 (Open Web Text)

Max Activating Token Index: 950

Text #2

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.7844. Min Act: -0.1700

Data Index: 7925998 (Open Web Text)

Max Activating Token Index: 803

Text #3

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.7452. Min Act: -0.1700

Data Index: 3374597 (Open Web Text)

Max Activating Token Index: 972

Text #4

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.6173. Min Act: -0.1700

Data Index: 6337428 (Open Web Text)

Max Activating Token Index: 499

Text #5

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.5504. Min Act: -0.1700

Data Index: 4625573 (Open Web Text)

Max Activating Token Index: 948

Text #6

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4981. Min Act: -0.1700

Data Index: 4701739 (Open Web Text)

Max Activating Token Index: 731

Text #7

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4182. Min Act: -0.1700

Data Index: 8027398 (Open Web Text)

Max Activating Token Index: 889

Text #8

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4601. Min Act: -0.1700

Data Index: 5284678 (Open Web Text)

Max Activating Token Index: 486

Text #9

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4317. Min Act: -0.1700

Data Index: 5037232 (Open Web Text)

Max Activating Token Index: 893

Text #10

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4971. Min Act: -0.1700

Data Index: 6034439 (Open Web Text)

Max Activating Token Index: 533

Text #11

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4314. Min Act: -0.1700

Data Index: 1029651 (Open Web Text)

Max Activating Token Index: 279

Text #12

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4184. Min Act: -0.1700

Data Index: 6263702 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4223. Min Act: -0.1700

Data Index: 1418066 (Open Web Text)

Max Activating Token Index: 10

Text #14

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.3754. Min Act: -0.1700

Data Index: 1688675 (Open Web Text)

Max Activating Token Index: 515

Text #15

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4151. Min Act: -0.1700

Data Index: 6225286 (Open Web Text)

Max Activating Token Index: 372

Text #16

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.4444. Min Act: -0.1700

Data Index: 1528192 (Open Web Text)

Max Activating Token Index: 189

Text #17

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.3018. Min Act: -0.1700

Data Index: 3547773 (Open Web Text)

Max Activating Token Index: 748

Text #18

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.3758. Min Act: -0.1700

Data Index: 3170322 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 5.8268. Min Range: -5.8268

Max Act: 5.3587. Min Act: -0.1700

Data Index: 8202790 (Open Web Text)

Max Activating Token Index: 683