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

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

Neuron 2069 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.8205. Min Act: -0.0000

Data Index: 960192 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.7277. Min Act: -0.0000

Data Index: 382630 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.5914. Min Act: -0.0000

Data Index: 584376 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.7047. Min Act: -0.0000

Data Index: 1164471 (C4 (Web Text))

Max Activating Token Index: 851

Text #4

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.8094. Min Act: -0.0000

Data Index: 684957 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.6044. Min Act: -0.0000

Data Index: 126412 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.7354. Min Act: -0.0000

Data Index: 508155 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.5700. Min Act: -0.0000

Data Index: 1045761 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.4111. Min Act: -0.0000

Data Index: 1305659 (C4 (Web Text))

Max Activating Token Index: 741

Text #9

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.4933. Min Act: -0.0000

Data Index: 725488 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.4868. Min Act: -0.0000

Data Index: 1178220 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.3549. Min Act: -0.0000

Data Index: 918855 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.4441. Min Act: -0.0000

Data Index: 889574 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.4316. Min Act: -0.0000

Data Index: 316062 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.4575. Min Act: -0.0000

Data Index: 342103 (C4 (Web Text))

Max Activating Token Index: 308

Text #15

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.3363. Min Act: -0.0000

Data Index: 1122039 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.3223. Min Act: -0.0000

Data Index: 47743 (C4 (Web Text))

Max Activating Token Index: 718

Text #17

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.3088. Min Act: -0.0000

Data Index: 14186 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.2917. Min Act: -0.0000

Data Index: 56651 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 2.8205. Min Range: -2.8205

Max Act: 2.2921. Min Act: -0.0000

Data Index: 427924 (C4 (Web Text))

Max Activating Token Index: 736