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

Dataset: Open Web Text

Neuron 928 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: 4.7279. Min Range: -4.7279

Max Act: 4.7245. Min Act: -0.1700

Data Index: 4782470 (Open Web Text)

Max Activating Token Index: 686

Text #1

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.7279. Min Act: -0.1700

Data Index: 7729937 (Open Web Text)

Max Activating Token Index: 178

Text #2

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.7047. Min Act: -0.1700

Data Index: 5189644 (Open Web Text)

Max Activating Token Index: 119

Text #3

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.6600. Min Act: -0.1700

Data Index: 4330270 (Open Web Text)

Max Activating Token Index: 257

Text #4

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.6502. Min Act: -0.1700

Data Index: 6740844 (Open Web Text)

Max Activating Token Index: 613

Text #5

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.6404. Min Act: -0.1700

Data Index: 2649484 (Open Web Text)

Max Activating Token Index: 922

Text #6

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5820. Min Act: -0.1700

Data Index: 324525 (Open Web Text)

Max Activating Token Index: 376

Text #7

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5634. Min Act: -0.1700

Data Index: 5742953 (Open Web Text)

Max Activating Token Index: 769

Text #8

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.6232. Min Act: -0.1700

Data Index: 4028211 (Open Web Text)

Max Activating Token Index: 492

Text #9

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5815. Min Act: -0.1700

Data Index: 5729747 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5413. Min Act: -0.1700

Data Index: 6748411 (Open Web Text)

Max Activating Token Index: 925

Text #11

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5061. Min Act: -0.1700

Data Index: 4018189 (Open Web Text)

Max Activating Token Index: 542

Text #12

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5332. Min Act: -0.1700

Data Index: 1189749 (Open Web Text)

Max Activating Token Index: 39

Text #13

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5232. Min Act: -0.1700

Data Index: 2325436 (Open Web Text)

Max Activating Token Index: 479

Text #14

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5365. Min Act: -0.1700

Data Index: 2392067 (Open Web Text)

Max Activating Token Index: 424

Text #15

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5246. Min Act: -0.1700

Data Index: 2529515 (Open Web Text)

Max Activating Token Index: 619

Text #16

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5234. Min Act: -0.1700

Data Index: 3780746 (Open Web Text)

Max Activating Token Index: 844

Text #17

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5177. Min Act: -0.1700

Data Index: 3717407 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.5178. Min Act: -0.1700

Data Index: 5220831 (Open Web Text)

Max Activating Token Index: 852

Text #19

Max Range: 4.7279. Min Range: -4.7279

Max Act: 4.4914. Min Act: -0.1700

Data Index: 4934269 (Open Web Text)

Max Activating Token Index: 538