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

Dataset: Open Web Text

Neuron 1847 in Layer 0

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: 1.3970. Min Range: -1.3970

Max Act: 1.3970. Min Act: -0.1080

Data Index: 8111304 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3840. Min Act: -0.1080

Data Index: 8635411 (Open Web Text)

Max Activating Token Index: 900

Text #2

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3821. Min Act: -0.1080

Data Index: 8635398 (Open Web Text)

Max Activating Token Index: 906

Text #3

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3938. Min Act: -0.1080

Data Index: 8635423 (Open Web Text)

Max Activating Token Index: 926

Text #4

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3870. Min Act: -0.1080

Data Index: 8635383 (Open Web Text)

Max Activating Token Index: 867

Text #5

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3884. Min Act: -0.1440

Data Index: 2666206 (Open Web Text)

Max Activating Token Index: 829

Text #6

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3931. Min Act: -0.1080

Data Index: 1026745 (Open Web Text)

Max Activating Token Index: 979

Text #7

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3861. Min Act: -0.1080

Data Index: 6823017 (Open Web Text)

Max Activating Token Index: 920

Text #8

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3821. Min Act: -0.1080

Data Index: 3000308 (Open Web Text)

Max Activating Token Index: 789

Text #9

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3793. Min Act: -0.1461

Data Index: 267492 (Open Web Text)

Max Activating Token Index: 830

Text #10

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3854. Min Act: -0.1080

Data Index: 4455750 (Open Web Text)

Max Activating Token Index: 735

Text #11

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3780. Min Act: -0.1080

Data Index: 7891642 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3857. Min Act: -0.1080

Data Index: 3551576 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3706. Min Act: -0.1080

Data Index: 5604503 (Open Web Text)

Max Activating Token Index: 102

Text #14

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3616. Min Act: -0.1080

Data Index: 7578090 (Open Web Text)

Max Activating Token Index: 255

Text #15

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3673. Min Act: -0.1080

Data Index: 3489848 (Open Web Text)

Max Activating Token Index: 310

Text #16

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3606. Min Act: -0.1080

Data Index: 8043527 (Open Web Text)

Max Activating Token Index: 98

Text #17

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3565. Min Act: -0.1080

Data Index: 7709919 (Open Web Text)

Max Activating Token Index: 272

Text #18

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3476. Min Act: -0.1080

Data Index: 1142424 (Open Web Text)

Max Activating Token Index: 894

Text #19

Max Range: 1.3970. Min Range: -1.3970

Max Act: 1.3537. Min Act: -0.1080

Data Index: 3551578 (Open Web Text)

Max Activating Token Index: 256