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

Dataset: Open Web Text

Neuron 789 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: 1.4187. Min Range: -1.4187

Max Act: 1.4187. Min Act: -0.1700

Data Index: 4952346 (Open Web Text)

Max Activating Token Index: 418

Text #1

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.4160. Min Act: -0.1700

Data Index: 8169832 (Open Web Text)

Max Activating Token Index: 58

Text #2

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.4080. Min Act: -0.1660

Data Index: 4717020 (Open Web Text)

Max Activating Token Index: 150

Text #3

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3887. Min Act: -0.1700

Data Index: 2897554 (Open Web Text)

Max Activating Token Index: 454

Text #4

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3896. Min Act: -0.1700

Data Index: 3199458 (Open Web Text)

Max Activating Token Index: 54

Text #5

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3851. Min Act: -0.1700

Data Index: 5664407 (Open Web Text)

Max Activating Token Index: 344

Text #6

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3884. Min Act: -0.1700

Data Index: 2951990 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3739. Min Act: -0.1700

Data Index: 6304985 (Open Web Text)

Max Activating Token Index: 1004

Text #8

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3753. Min Act: -0.1699

Data Index: 8504391 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3727. Min Act: -0.1700

Data Index: 7168530 (Open Web Text)

Max Activating Token Index: 449

Text #10

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3819. Min Act: -0.1700

Data Index: 1498313 (Open Web Text)

Max Activating Token Index: 701

Text #11

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3815. Min Act: -0.1700

Data Index: 2828235 (Open Web Text)

Max Activating Token Index: 405

Text #12

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3788. Min Act: -0.1700

Data Index: 7442174 (Open Web Text)

Max Activating Token Index: 938

Text #13

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3675. Min Act: -0.1700

Data Index: 8097484 (Open Web Text)

Max Activating Token Index: 565

Text #14

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3647. Min Act: -0.1700

Data Index: 5467217 (Open Web Text)

Max Activating Token Index: 148

Text #15

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3770. Min Act: -0.1698

Data Index: 2023774 (Open Web Text)

Max Activating Token Index: 130

Text #16

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3662. Min Act: -0.1700

Data Index: 3531777 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3630. Min Act: -0.1700

Data Index: 4201658 (Open Web Text)

Max Activating Token Index: 384

Text #18

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3583. Min Act: -0.1700

Data Index: 349305 (Open Web Text)

Max Activating Token Index: 184

Text #19

Max Range: 1.4187. Min Range: -1.4187

Max Act: 1.3573. Min Act: -0.1700

Data Index: 7687173 (Open Web Text)

Max Activating Token Index: 403