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

Dataset: Open Web Text

Neuron 332 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: 4.4175. Min Range: -4.4175

Max Act: 4.4175. Min Act: -0.1700

Data Index: 939039 (Open Web Text)

Max Activating Token Index: 98

Text #1

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.3160. Min Act: -0.1700

Data Index: 1731938 (Open Web Text)

Max Activating Token Index: 36

Text #2

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2831. Min Act: -0.1700

Data Index: 6878789 (Open Web Text)

Max Activating Token Index: 307

Text #3

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.3344. Min Act: -0.1700

Data Index: 5545955 (Open Web Text)

Max Activating Token Index: 10

Text #4

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2999. Min Act: -0.1700

Data Index: 8711820 (Open Web Text)

Max Activating Token Index: 55

Text #5

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2896. Min Act: -0.1700

Data Index: 5985967 (Open Web Text)

Max Activating Token Index: 441

Text #6

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2977. Min Act: -0.1700

Data Index: 6196592 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2709. Min Act: -0.1699

Data Index: 5901017 (Open Web Text)

Max Activating Token Index: 18

Text #8

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2900. Min Act: -0.1700

Data Index: 8065456 (Open Web Text)

Max Activating Token Index: 202

Text #9

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.3028. Min Act: -0.1700

Data Index: 193344 (Open Web Text)

Max Activating Token Index: 622

Text #10

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2845. Min Act: -0.1700

Data Index: 3162904 (Open Web Text)

Max Activating Token Index: 26

Text #11

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2508. Min Act: -0.1700

Data Index: 2244519 (Open Web Text)

Max Activating Token Index: 29

Text #12

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2639. Min Act: -0.1700

Data Index: 438511 (Open Web Text)

Max Activating Token Index: 61

Text #13

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2596. Min Act: -0.1700

Data Index: 5565509 (Open Web Text)

Max Activating Token Index: 674

Text #14

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2503. Min Act: -0.1700

Data Index: 7509470 (Open Web Text)

Max Activating Token Index: 1009

Text #15

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2776. Min Act: -0.1700

Data Index: 1379141 (Open Web Text)

Max Activating Token Index: 695

Text #16

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2661. Min Act: -0.1700

Data Index: 4411056 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2270. Min Act: -0.1700

Data Index: 657272 (Open Web Text)

Max Activating Token Index: 579

Text #18

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2405. Min Act: -0.1700

Data Index: 5948089 (Open Web Text)

Max Activating Token Index: 281

Text #19

Max Range: 4.4175. Min Range: -4.4175

Max Act: 4.2343. Min Act: -0.1700

Data Index: 3580883 (Open Web Text)

Max Activating Token Index: 70