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

Dataset: Open Web Text

Neuron 2676 in Layer 5

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: 4.5027. Min Range: -4.5027

Max Act: 4.5027. Min Act: -0.1700

Data Index: 7311717 (Open Web Text)

Max Activating Token Index: 454

Text #1

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.3498. Min Act: -0.1700

Data Index: 6085582 (Open Web Text)

Max Activating Token Index: 917

Text #2

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.3593. Min Act: -0.1700

Data Index: 8372846 (Open Web Text)

Max Activating Token Index: 521

Text #3

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.3159. Min Act: -0.1700

Data Index: 1171686 (Open Web Text)

Max Activating Token Index: 553

Text #4

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.3316. Min Act: -0.1700

Data Index: 625244 (Open Web Text)

Max Activating Token Index: 658

Text #5

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.3258. Min Act: -0.1700

Data Index: 3378018 (Open Web Text)

Max Activating Token Index: 377

Text #6

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2959. Min Act: -0.1700

Data Index: 8322362 (Open Web Text)

Max Activating Token Index: 360

Text #7

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.3179. Min Act: -0.1700

Data Index: 5638225 (Open Web Text)

Max Activating Token Index: 517

Text #8

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2440. Min Act: -0.1700

Data Index: 5197312 (Open Web Text)

Max Activating Token Index: 256

Text #9

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2203. Min Act: -0.1700

Data Index: 1605319 (Open Web Text)

Max Activating Token Index: 231

Text #10

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2455. Min Act: -0.1700

Data Index: 4009415 (Open Web Text)

Max Activating Token Index: 667

Text #11

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2100. Min Act: -0.1700

Data Index: 7866867 (Open Web Text)

Max Activating Token Index: 76

Text #12

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2314. Min Act: -0.1700

Data Index: 4684720 (Open Web Text)

Max Activating Token Index: 299

Text #13

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.1977. Min Act: -0.1700

Data Index: 6510702 (Open Web Text)

Max Activating Token Index: 730

Text #14

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2190. Min Act: -0.1700

Data Index: 1601716 (Open Web Text)

Max Activating Token Index: 434

Text #15

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.1981. Min Act: -0.1700

Data Index: 6022411 (Open Web Text)

Max Activating Token Index: 155

Text #16

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2145. Min Act: -0.1700

Data Index: 7808927 (Open Web Text)

Max Activating Token Index: 559

Text #17

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.1828. Min Act: -0.1700

Data Index: 2372302 (Open Web Text)

Max Activating Token Index: 971

Text #18

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.2099. Min Act: -0.1700

Data Index: 2328350 (Open Web Text)

Max Activating Token Index: 624

Text #19

Max Range: 4.5027. Min Range: -4.5027

Max Act: 4.1934. Min Act: -0.1700

Data Index: 247071 (Open Web Text)

Max Activating Token Index: 540