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

Dataset: Open Web Text

Neuron 1604 in Layer 2

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: 3.4762. Min Range: -3.4762

Max Act: 3.4762. Min Act: -0.1700

Data Index: 359785 (Open Web Text)

Max Activating Token Index: 859

Text #1

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.4188. Min Act: -0.1700

Data Index: 1002827 (Open Web Text)

Max Activating Token Index: 803

Text #2

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.4148. Min Act: -0.1700

Data Index: 8388381 (Open Web Text)

Max Activating Token Index: 134

Text #3

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3792. Min Act: -0.1700

Data Index: 5105529 (Open Web Text)

Max Activating Token Index: 400

Text #4

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.4050. Min Act: -0.1700

Data Index: 5422714 (Open Web Text)

Max Activating Token Index: 188

Text #5

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3906. Min Act: -0.1700

Data Index: 7985155 (Open Web Text)

Max Activating Token Index: 664

Text #6

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3581. Min Act: -0.1700

Data Index: 1131415 (Open Web Text)

Max Activating Token Index: 896

Text #7

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3722. Min Act: -0.1700

Data Index: 4156649 (Open Web Text)

Max Activating Token Index: 158

Text #8

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3998. Min Act: -0.1700

Data Index: 1611852 (Open Web Text)

Max Activating Token Index: 208

Text #9

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3722. Min Act: -0.1700

Data Index: 2526600 (Open Web Text)

Max Activating Token Index: 295

Text #10

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3610. Min Act: -0.1700

Data Index: 3391659 (Open Web Text)

Max Activating Token Index: 173

Text #11

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3815. Min Act: -0.1700

Data Index: 2646966 (Open Web Text)

Max Activating Token Index: 328

Text #12

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3484. Min Act: -0.1700

Data Index: 3926205 (Open Web Text)

Max Activating Token Index: 701

Text #13

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3768. Min Act: -0.1700

Data Index: 4075369 (Open Web Text)

Max Activating Token Index: 14

Text #14

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3565. Min Act: -0.1700

Data Index: 2133430 (Open Web Text)

Max Activating Token Index: 44

Text #15

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3535. Min Act: -0.1700

Data Index: 8469010 (Open Web Text)

Max Activating Token Index: 889

Text #16

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3342. Min Act: -0.1700

Data Index: 7702347 (Open Web Text)

Max Activating Token Index: 995

Text #17

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3642. Min Act: -0.1700

Data Index: 7522274 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3239. Min Act: -0.1700

Data Index: 2664415 (Open Web Text)

Max Activating Token Index: 548

Text #19

Max Range: 3.4762. Min Range: -3.4762

Max Act: 3.3146. Min Act: -0.1700

Data Index: 6818778 (Open Web Text)

Max Activating Token Index: 70