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

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

Neuron 168 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.3061. Min Range: -6.3061

Max Act: 5.6525. Min Act: -0.0000

Data Index: 933652 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 6.3061. Min Range: -6.3061

Max Act: 6.3061. Min Act: -0.0000

Data Index: 1241273 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 6.3061. Min Range: -6.3061

Max Act: 6.2119. Min Act: -0.0000

Data Index: 174895 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 6.3061. Min Range: -6.3061

Max Act: 5.4643. Min Act: -0.0000

Data Index: 943082 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.9733. Min Act: -0.0000

Data Index: 1137812 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.9462. Min Act: -0.0000

Data Index: 198822 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 6.3061. Min Range: -6.3061

Max Act: 5.2334. Min Act: -0.0000

Data Index: 1055289 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.8578. Min Act: -0.0000

Data Index: 659421 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.7368. Min Act: -0.0000

Data Index: 36617 (C4 (Web Text))

Max Activating Token Index: 474

Text #9

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.8274. Min Act: -0.0000

Data Index: 298569 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.9709. Min Act: -0.0000

Data Index: 1132071 (C4 (Web Text))

Max Activating Token Index: 184

Text #11

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.8744. Min Act: -0.0000

Data Index: 1062992 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 6.3061. Min Range: -6.3061

Max Act: 5.0566. Min Act: -0.0000

Data Index: 145211 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.6651. Min Act: -0.0000

Data Index: 374435 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.4594. Min Act: -0.0000

Data Index: 147426 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.4488. Min Act: -0.0000

Data Index: 1286399 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.7825. Min Act: -0.0000

Data Index: 436441 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.7193. Min Act: -0.0000

Data Index: 1279111 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.7427. Min Act: -0.0000

Data Index: 1268998 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 6.3061. Min Range: -6.3061

Max Act: 4.3331. Min Act: -0.0000

Data Index: 332289 (C4 (Web Text))

Max Activating Token Index: 602