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

Dataset: Open Web Text

Neuron 2352 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: 4.1213. Min Range: -4.1213

Max Act: 4.1213. Min Act: -0.1700

Data Index: 5094268 (Open Web Text)

Max Activating Token Index: 704

Text #1

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.9486. Min Act: -0.1700

Data Index: 4791826 (Open Web Text)

Max Activating Token Index: 657

Text #2

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.8663. Min Act: -0.1700

Data Index: 6256023 (Open Web Text)

Max Activating Token Index: 576

Text #3

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.8237. Min Act: -0.1700

Data Index: 2299856 (Open Web Text)

Max Activating Token Index: 185

Text #4

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.8503. Min Act: -0.1700

Data Index: 2929409 (Open Web Text)

Max Activating Token Index: 980

Text #5

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7681. Min Act: -0.1700

Data Index: 2422498 (Open Web Text)

Max Activating Token Index: 399

Text #6

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7774. Min Act: -0.1700

Data Index: 8830400 (Open Web Text)

Max Activating Token Index: 814

Text #7

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7698. Min Act: -0.1700

Data Index: 1129652 (Open Web Text)

Max Activating Token Index: 173

Text #8

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7525. Min Act: -0.1700

Data Index: 6990323 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7858. Min Act: -0.1700

Data Index: 5764430 (Open Web Text)

Max Activating Token Index: 642

Text #10

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7599. Min Act: -0.1700

Data Index: 3357608 (Open Web Text)

Max Activating Token Index: 870

Text #11

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7603. Min Act: -0.1700

Data Index: 7498524 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7509. Min Act: -0.1700

Data Index: 5695922 (Open Web Text)

Max Activating Token Index: 843

Text #13

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7485. Min Act: -0.1700

Data Index: 1575396 (Open Web Text)

Max Activating Token Index: 973

Text #14

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7132. Min Act: -0.1700

Data Index: 1179858 (Open Web Text)

Max Activating Token Index: 901

Text #15

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.6999. Min Act: -0.1700

Data Index: 8159320 (Open Web Text)

Max Activating Token Index: 680

Text #16

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.6858. Min Act: -0.1700

Data Index: 6430618 (Open Web Text)

Max Activating Token Index: 463

Text #17

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7425. Min Act: -0.1700

Data Index: 4996725 (Open Web Text)

Max Activating Token Index: 985

Text #18

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.7377. Min Act: -0.1700

Data Index: 498210 (Open Web Text)

Max Activating Token Index: 573

Text #19

Max Range: 4.1213. Min Range: -4.1213

Max Act: 3.6852. Min Act: -0.1700

Data Index: 1977233 (Open Web Text)

Max Activating Token Index: 645