Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 566 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0032. Min Act: -0.0006

Data Index: 222995 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0006

Data Index: 1294492 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0028. Min Act: -0.0006

Data Index: 482399 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0027. Min Act: -0.0006

Data Index: 49637 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0026. Min Act: -0.0006

Data Index: 277614 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0026. Min Act: -0.0006

Data Index: 533660 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0026. Min Act: -0.0007

Data Index: 668737 (C4 (Web Text))

Max Activating Token Index: 851

Text #7

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0006

Data Index: 546882 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0025. Min Act: -0.0006

Data Index: 466049 (C4 (Web Text))

Max Activating Token Index: 450

Text #9

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 1161908 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 624737 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 174561 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 313323 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 268594 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 77705 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0024. Min Act: -0.0006

Data Index: 1047715 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0023. Min Act: -0.0006

Data Index: 1100960 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0023. Min Act: -0.0006

Data Index: 659439 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0023. Min Act: -0.0006

Data Index: 1194267 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.0032. Min Range: -0.0032

Max Act: 0.0023. Min Act: -0.0006

Data Index: 202600 (C4 (Web Text))

Max Activating Token Index: 456