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

Dataset: Open Web Text

Neuron 2539 in Layer 1

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: 4.1769. Min Range: -4.1769

Max Act: 4.1769. Min Act: -0.1700

Data Index: 4147004 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0549. Min Act: -0.1700

Data Index: 5800479 (Open Web Text)

Max Activating Token Index: 979

Text #2

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0731. Min Act: -0.1700

Data Index: 445881 (Open Web Text)

Max Activating Token Index: 79

Text #3

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0333. Min Act: -0.1700

Data Index: 4892795 (Open Web Text)

Max Activating Token Index: 369

Text #4

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0374. Min Act: -0.1700

Data Index: 4775303 (Open Web Text)

Max Activating Token Index: 469

Text #5

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0236. Min Act: -0.1700

Data Index: 4527958 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0295. Min Act: -0.1700

Data Index: 8557009 (Open Web Text)

Max Activating Token Index: 30

Text #7

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0198. Min Act: -0.1700

Data Index: 8540768 (Open Web Text)

Max Activating Token Index: 436

Text #8

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0294. Min Act: -0.1700

Data Index: 3920047 (Open Web Text)

Max Activating Token Index: 277

Text #9

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0446. Min Act: -0.1700

Data Index: 1564135 (Open Web Text)

Max Activating Token Index: 379

Text #10

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0429. Min Act: -0.1700

Data Index: 7810804 (Open Web Text)

Max Activating Token Index: 80

Text #11

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0270. Min Act: -0.1700

Data Index: 7729931 (Open Web Text)

Max Activating Token Index: 435

Text #12

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0306. Min Act: -0.1700

Data Index: 3233495 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0358. Min Act: -0.1700

Data Index: 6921089 (Open Web Text)

Max Activating Token Index: 686

Text #14

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0231. Min Act: -0.1700

Data Index: 2412352 (Open Web Text)

Max Activating Token Index: 310

Text #15

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0210. Min Act: -0.1700

Data Index: 6643104 (Open Web Text)

Max Activating Token Index: 932

Text #16

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9958. Min Act: -0.1700

Data Index: 1684281 (Open Web Text)

Max Activating Token Index: 945

Text #17

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9985. Min Act: -0.1700

Data Index: 731565 (Open Web Text)

Max Activating Token Index: 352

Text #18

Max Range: 4.1769. Min Range: -4.1769

Max Act: 3.9969. Min Act: -0.1700

Data Index: 788058 (Open Web Text)

Max Activating Token Index: 111

Text #19

Max Range: 4.1769. Min Range: -4.1769

Max Act: 4.0020. Min Act: -0.1700

Data Index: 4878349 (Open Web Text)

Max Activating Token Index: 144