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

Dataset: Open Web Text

Neuron 1574 in Layer 3

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: 4.8150. Min Range: -4.8150

Max Act: 4.7625. Min Act: -0.1700

Data Index: 3794083 (Open Web Text)

Max Activating Token Index: 539

Text #1

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.8150. Min Act: -0.1700

Data Index: 4982655 (Open Web Text)

Max Activating Token Index: 885

Text #2

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6941. Min Act: -0.1700

Data Index: 4360902 (Open Web Text)

Max Activating Token Index: 382

Text #3

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6820. Min Act: -0.1700

Data Index: 2172533 (Open Web Text)

Max Activating Token Index: 216

Text #4

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6710. Min Act: -0.1700

Data Index: 177687 (Open Web Text)

Max Activating Token Index: 64

Text #5

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6884. Min Act: -0.1700

Data Index: 5782603 (Open Web Text)

Max Activating Token Index: 369

Text #6

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6058. Min Act: -0.1700

Data Index: 5104119 (Open Web Text)

Max Activating Token Index: 624

Text #7

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5935. Min Act: -0.1700

Data Index: 8485344 (Open Web Text)

Max Activating Token Index: 494

Text #8

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6059. Min Act: -0.1700

Data Index: 4609000 (Open Web Text)

Max Activating Token Index: 573

Text #9

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6069. Min Act: -0.1700

Data Index: 604036 (Open Web Text)

Max Activating Token Index: 42

Text #10

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5492. Min Act: -0.1700

Data Index: 2426101 (Open Web Text)

Max Activating Token Index: 50

Text #11

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5752. Min Act: -0.1700

Data Index: 4447753 (Open Web Text)

Max Activating Token Index: 62

Text #12

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5842. Min Act: -0.1700

Data Index: 3041135 (Open Web Text)

Max Activating Token Index: 77

Text #13

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6039. Min Act: -0.1700

Data Index: 7273878 (Open Web Text)

Max Activating Token Index: 1003

Text #14

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.6043. Min Act: -0.1700

Data Index: 6762663 (Open Web Text)

Max Activating Token Index: 243

Text #15

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5688. Min Act: -0.1700

Data Index: 6820412 (Open Web Text)

Max Activating Token Index: 735

Text #16

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5627. Min Act: -0.1700

Data Index: 1555159 (Open Web Text)

Max Activating Token Index: 504

Text #17

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5504. Min Act: -0.1700

Data Index: 5912842 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5567. Min Act: -0.1700

Data Index: 400596 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 4.8150. Min Range: -4.8150

Max Act: 4.5695. Min Act: -0.1700

Data Index: 6548069 (Open Web Text)

Max Activating Token Index: 777