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

Dataset: Open Web Text

Neuron 2831 in Layer 1

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: 1.4340. Min Range: -1.4340

Max Act: 1.4340. Min Act: -0.1700

Data Index: 4745431 (Open Web Text)

Max Activating Token Index: 87

Text #1

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.4263. Min Act: -0.1700

Data Index: 4467255 (Open Web Text)

Max Activating Token Index: 126

Text #2

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3961. Min Act: -0.1700

Data Index: 7553004 (Open Web Text)

Max Activating Token Index: 52

Text #3

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3830. Min Act: -0.1700

Data Index: 2274135 (Open Web Text)

Max Activating Token Index: 196

Text #4

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3928. Min Act: -0.1700

Data Index: 6826172 (Open Web Text)

Max Activating Token Index: 449

Text #5

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3864. Min Act: -0.1700

Data Index: 5809495 (Open Web Text)

Max Activating Token Index: 385

Text #6

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3734. Min Act: -0.1697

Data Index: 8255921 (Open Web Text)

Max Activating Token Index: 554

Text #7

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3695. Min Act: -0.1699

Data Index: 6912096 (Open Web Text)

Max Activating Token Index: 585

Text #8

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3714. Min Act: -0.1700

Data Index: 3819508 (Open Web Text)

Max Activating Token Index: 160

Text #9

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3690. Min Act: -0.1699

Data Index: 1634892 (Open Web Text)

Max Activating Token Index: 165

Text #10

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3833. Min Act: -0.1699

Data Index: 5127356 (Open Web Text)

Max Activating Token Index: 979

Text #11

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3724. Min Act: -0.1699

Data Index: 4291269 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3726. Min Act: -0.1700

Data Index: 3254602 (Open Web Text)

Max Activating Token Index: 598

Text #13

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3593. Min Act: -0.1700

Data Index: 80726 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3625. Min Act: -0.1700

Data Index: 8591231 (Open Web Text)

Max Activating Token Index: 498

Text #15

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3620. Min Act: -0.1700

Data Index: 7217547 (Open Web Text)

Max Activating Token Index: 221

Text #16

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3714. Min Act: -0.1696

Data Index: 4993139 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3666. Min Act: -0.1700

Data Index: 3525536 (Open Web Text)

Max Activating Token Index: 247

Text #18

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3710. Min Act: -0.1698

Data Index: 7130368 (Open Web Text)

Max Activating Token Index: 674

Text #19

Max Range: 1.4340. Min Range: -1.4340

Max Act: 1.3539. Min Act: -0.1700

Data Index: 4648447 (Open Web Text)

Max Activating Token Index: 627