Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8588. Min Act: -0.0003

Data Index: 598871 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8711. Min Act: -0.0003

Data Index: 212086 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8573. Min Act: -0.0003

Data Index: 959313 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7519. Min Act: -0.0003

Data Index: 170695 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7273. Min Act: -0.0003

Data Index: 8415 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7257. Min Act: -0.0003

Data Index: 510669 (C4 (Web Text))

Max Activating Token Index: 497

Text #6

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8065. Min Act: -0.0003

Data Index: 436245 (C4 (Web Text))

Max Activating Token Index: 618

Text #7

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.7303. Min Act: -0.0003

Data Index: 1304037 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.8072. Min Act: -0.0003

Data Index: 443145 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6297. Min Act: -0.0003

Data Index: 111330 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6671. Min Act: -0.0003

Data Index: 1245711 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6218. Min Act: -0.0003

Data Index: 1199310 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.5989. Min Act: -0.0003

Data Index: 1256434 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6334. Min Act: -0.0003

Data Index: 1137734 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6117. Min Act: -0.0003

Data Index: 149177 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6301. Min Act: -0.0003

Data Index: 591019 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6107. Min Act: -0.0003

Data Index: 116298 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6278. Min Act: -0.0003

Data Index: 329078 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6143. Min Act: -0.0003

Data Index: 318244 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.8711. Min Range: -0.8711

Max Act: 0.6110. Min Act: -0.0003

Data Index: 15060 (C4 (Web Text))

Max Activating Token Index: 663