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

Dataset: Open Web Text

Neuron 2012 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: 3.2192. Min Range: -3.2192

Max Act: 3.2129. Min Act: -0.1700

Data Index: 7662431 (Open Web Text)

Max Activating Token Index: 813

Text #1

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.2192. Min Act: -0.1700

Data Index: 2665135 (Open Web Text)

Max Activating Token Index: 776

Text #2

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1998. Min Act: -0.1700

Data Index: 5144916 (Open Web Text)

Max Activating Token Index: 976

Text #3

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1569. Min Act: -0.1700

Data Index: 2655728 (Open Web Text)

Max Activating Token Index: 450

Text #4

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1337. Min Act: -0.1700

Data Index: 3761175 (Open Web Text)

Max Activating Token Index: 597

Text #5

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1456. Min Act: -0.1700

Data Index: 1032371 (Open Web Text)

Max Activating Token Index: 267

Text #6

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0936. Min Act: -0.1700

Data Index: 546326 (Open Web Text)

Max Activating Token Index: 1016

Text #7

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1174. Min Act: -0.1700

Data Index: 7934266 (Open Web Text)

Max Activating Token Index: 432

Text #8

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.1204. Min Act: -0.1700

Data Index: 3384239 (Open Web Text)

Max Activating Token Index: 964

Text #9

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0899. Min Act: -0.1700

Data Index: 1072037 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0755. Min Act: -0.1700

Data Index: 2111313 (Open Web Text)

Max Activating Token Index: 38

Text #11

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0712. Min Act: -0.1700

Data Index: 2835361 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0678. Min Act: -0.1700

Data Index: 1846496 (Open Web Text)

Max Activating Token Index: 119

Text #13

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0637. Min Act: -0.1700

Data Index: 4683067 (Open Web Text)

Max Activating Token Index: 754

Text #14

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0959. Min Act: -0.1700

Data Index: 1867628 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0791. Min Act: -0.1700

Data Index: 8370765 (Open Web Text)

Max Activating Token Index: 288

Text #16

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0556. Min Act: -0.1700

Data Index: 8234436 (Open Web Text)

Max Activating Token Index: 255

Text #17

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0592. Min Act: -0.1700

Data Index: 2531248 (Open Web Text)

Max Activating Token Index: 459

Text #18

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0404. Min Act: -0.1700

Data Index: 3817260 (Open Web Text)

Max Activating Token Index: 306

Text #19

Max Range: 3.2192. Min Range: -3.2192

Max Act: 3.0467. Min Act: -0.1700

Data Index: 2643861 (Open Web Text)

Max Activating Token Index: 745