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

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

Neuron 3093 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1336. Min Act: -0.0000

Data Index: 906423 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0977. Min Act: -0.0000

Data Index: 362186 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1001. Min Act: -0.0000

Data Index: 292045 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.1025. Min Act: -0.0000

Data Index: 381174 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0970. Min Act: -0.0000

Data Index: 616538 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0897. Min Act: -0.0000

Data Index: 620108 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0946. Min Act: -0.0000

Data Index: 65594 (C4 (Web Text))

Max Activating Token Index: 871

Text #7

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0916. Min Act: -0.0000

Data Index: 544022 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0909. Min Act: -0.0000

Data Index: 160524 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0890. Min Act: -0.0000

Data Index: 747177 (C4 (Web Text))

Max Activating Token Index: 671

Text #10

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0878. Min Act: -0.0000

Data Index: 84142 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0798. Min Act: -0.0000

Data Index: 142493 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0821. Min Act: -0.0000

Data Index: 242358 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0842. Min Act: -0.0000

Data Index: 156190 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1038132 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0873. Min Act: -0.0000

Data Index: 109974 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1127277 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0760. Min Act: -0.0000

Data Index: 1086374 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0868. Min Act: -0.0000

Data Index: 926038 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.1336. Min Range: -0.1336

Max Act: 0.0798. Min Act: -0.0000

Data Index: 835312 (C4 (Web Text))

Max Activating Token Index: 126