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

Dataset: Open Web Text

Neuron 1572 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: 4.3630. Min Range: -4.3630

Max Act: 4.3630. Min Act: -0.1700

Data Index: 5675338 (Open Web Text)

Max Activating Token Index: 125

Text #1

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.3410. Min Act: -0.1700

Data Index: 7933563 (Open Web Text)

Max Activating Token Index: 690

Text #2

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.3504. Min Act: -0.1700

Data Index: 5048676 (Open Web Text)

Max Activating Token Index: 369

Text #3

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.3195. Min Act: -0.1700

Data Index: 5636706 (Open Web Text)

Max Activating Token Index: 421

Text #4

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2935. Min Act: -0.1700

Data Index: 1774040 (Open Web Text)

Max Activating Token Index: 460

Text #5

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.3112. Min Act: -0.1700

Data Index: 7652529 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.3188. Min Act: -0.1700

Data Index: 5056533 (Open Web Text)

Max Activating Token Index: 790

Text #7

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.3078. Min Act: -0.1700

Data Index: 5084528 (Open Web Text)

Max Activating Token Index: 934

Text #8

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2340. Min Act: -0.1700

Data Index: 5029709 (Open Web Text)

Max Activating Token Index: 831

Text #9

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2410. Min Act: -0.1700

Data Index: 1262558 (Open Web Text)

Max Activating Token Index: 221

Text #10

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2661. Min Act: -0.1700

Data Index: 6585163 (Open Web Text)

Max Activating Token Index: 529

Text #11

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2890. Min Act: -0.1700

Data Index: 230617 (Open Web Text)

Max Activating Token Index: 923

Text #12

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2748. Min Act: -0.1700

Data Index: 913006 (Open Web Text)

Max Activating Token Index: 475

Text #13

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2394. Min Act: -0.1700

Data Index: 6053196 (Open Web Text)

Max Activating Token Index: 181

Text #14

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2184. Min Act: -0.1700

Data Index: 6049789 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2213. Min Act: -0.1700

Data Index: 5840299 (Open Web Text)

Max Activating Token Index: 110

Text #16

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2241. Min Act: -0.1700

Data Index: 4100720 (Open Web Text)

Max Activating Token Index: 508

Text #17

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2500. Min Act: -0.1700

Data Index: 1390195 (Open Web Text)

Max Activating Token Index: 800

Text #18

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2275. Min Act: -0.1700

Data Index: 4230882 (Open Web Text)

Max Activating Token Index: 27

Text #19

Max Range: 4.3630. Min Range: -4.3630

Max Act: 4.2358. Min Act: -0.1700

Data Index: 7762786 (Open Web Text)

Max Activating Token Index: 614