Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1021 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3901. Min Act: -0.0003

Data Index: 1014458 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3865. Min Act: -0.0004

Data Index: 1239316 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3979. Min Act: -0.0003

Data Index: 353465 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3910. Min Act: -0.0003

Data Index: 116031 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3445. Min Act: -0.0004

Data Index: 133170 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3350. Min Act: -0.0003

Data Index: 82460 (C4 (Web Text))

Max Activating Token Index: 426

Text #6

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3361. Min Act: -0.0004

Data Index: 491587 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3228. Min Act: -0.0004

Data Index: 679386 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3352. Min Act: -0.0004

Data Index: 516594 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3169. Min Act: -0.0003

Data Index: 47377 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3275. Min Act: -0.0004

Data Index: 667201 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3341. Min Act: -0.0003

Data Index: 110046 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3122. Min Act: -0.0003

Data Index: 148626 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3228. Min Act: -0.0004

Data Index: 758251 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3121. Min Act: -0.0003

Data Index: 72042 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3219. Min Act: -0.0003

Data Index: 941131 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2950. Min Act: -0.0003

Data Index: 949936 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3087. Min Act: -0.0003

Data Index: 758046 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2979. Min Act: -0.0003

Data Index: 280468 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3093. Min Act: -0.0003

Data Index: 257358 (C4 (Web Text))

Max Activating Token Index: 279