Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4507 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1150468 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.3038. Min Act: -0.0000

Data Index: 49021 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.3655. Min Act: -0.0000

Data Index: 967047 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.3695. Min Act: -0.0000

Data Index: 258669 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.4122. Min Act: -0.0000

Data Index: 762105 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.3430. Min Act: -0.0000

Data Index: 272877 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.2066. Min Act: -0.0000

Data Index: 1211206 (C4 (Web Text))

Max Activating Token Index: 194

Text #7

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.2529. Min Act: -0.0000

Data Index: 67702 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.1177. Min Act: -0.0000

Data Index: 467050 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0597. Min Act: -0.0000

Data Index: 727443 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0820. Min Act: -0.0000

Data Index: 268879 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0211. Min Act: 0.0000

Data Index: 712529 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1267488 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0225. Min Act: -0.0000

Data Index: 1289080 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0417. Min Act: -0.0000

Data Index: 284632 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.5766. Min Range: -1.5766

Max Act: 1.0254. Min Act: -0.0000

Data Index: 222629 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9503. Min Act: -0.0000

Data Index: 933189 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9713. Min Act: -0.0000

Data Index: 647819 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9648. Min Act: -0.0000

Data Index: 1039210 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 1.5766. Min Range: -1.5766

Max Act: 0.9520. Min Act: -0.0000

Data Index: 303099 (C4 (Web Text))

Max Activating Token Index: 1000