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

Dataset: Open Web Text

Neuron 2954 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 6.0000. Min Range: -6.0000

Max Act: 6.0000. Min Act: -0.1700

Data Index: 7163457 (Open Web Text)

Max Activating Token Index: 885

Text #1

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.7631. Min Act: -0.1700

Data Index: 869211 (Open Web Text)

Max Activating Token Index: 789

Text #2

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.7311. Min Act: -0.1700

Data Index: 7144066 (Open Web Text)

Max Activating Token Index: 433

Text #3

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.7379. Min Act: -0.1700

Data Index: 665271 (Open Web Text)

Max Activating Token Index: 107

Text #4

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6768. Min Act: -0.1700

Data Index: 110009 (Open Web Text)

Max Activating Token Index: 828

Text #5

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6742. Min Act: -0.1700

Data Index: 3696947 (Open Web Text)

Max Activating Token Index: 785

Text #6

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6049. Min Act: -0.1700

Data Index: 7362953 (Open Web Text)

Max Activating Token Index: 712

Text #7

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6496. Min Act: -0.1700

Data Index: 688673 (Open Web Text)

Max Activating Token Index: 812

Text #8

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6528. Min Act: -0.1700

Data Index: 7838227 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6070. Min Act: -0.1700

Data Index: 4473241 (Open Web Text)

Max Activating Token Index: 483

Text #10

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6075. Min Act: -0.1700

Data Index: 6565570 (Open Web Text)

Max Activating Token Index: 592

Text #11

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5941. Min Act: -0.1700

Data Index: 6321972 (Open Web Text)

Max Activating Token Index: 765

Text #12

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5964. Min Act: -0.1700

Data Index: 8693053 (Open Web Text)

Max Activating Token Index: 500

Text #13

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6007. Min Act: -0.1700

Data Index: 965141 (Open Web Text)

Max Activating Token Index: 384

Text #14

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.6131. Min Act: -0.1700

Data Index: 8464874 (Open Web Text)

Max Activating Token Index: 832

Text #15

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5992. Min Act: -0.1700

Data Index: 5878274 (Open Web Text)

Max Activating Token Index: 857

Text #16

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5324. Min Act: -0.1700

Data Index: 856819 (Open Web Text)

Max Activating Token Index: 494

Text #17

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5450. Min Act: -0.1700

Data Index: 1452488 (Open Web Text)

Max Activating Token Index: 105

Text #18

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5660. Min Act: -0.1700

Data Index: 4994614 (Open Web Text)

Max Activating Token Index: 702

Text #19

Max Range: 6.0000. Min Range: -6.0000

Max Act: 5.5318. Min Act: -0.1700

Data Index: 257462 (Open Web Text)

Max Activating Token Index: 937