Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2683 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6826. Min Act: -0.0000

Data Index: 357172 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6095. Min Act: -0.0000

Data Index: 915389 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6097. Min Act: -0.0000

Data Index: 102224 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.6131. Min Act: -0.0000

Data Index: 825816 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5668. Min Act: -0.0000

Data Index: 20035 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5770. Min Act: -0.0001

Data Index: 1255079 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5244. Min Act: -0.0000

Data Index: 814469 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5378. Min Act: -0.0000

Data Index: 736841 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.5136. Min Act: -0.0000

Data Index: 529151 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4577. Min Act: -0.0001

Data Index: 517764 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1008906 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4542. Min Act: -0.0001

Data Index: 373226 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4077. Min Act: -0.0000

Data Index: 416705 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4849. Min Act: -0.0000

Data Index: 708417 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1328932 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4545. Min Act: -0.0000

Data Index: 724469 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4039. Min Act: -0.0000

Data Index: 905694 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.4081. Min Act: -0.0000

Data Index: 766228 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3846. Min Act: -0.0001

Data Index: 742670 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 0.6826. Min Range: -0.6826

Max Act: 0.3771. Min Act: -0.0000

Data Index: 913232 (C4 (Web Text))

Max Activating Token Index: 308