Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 163 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1303563 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7563. Min Act: -0.0000

Data Index: 810219 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1107107 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7157. Min Act: -0.0000

Data Index: 219427 (C4 (Web Text))

Max Activating Token Index: 1008

Text #4

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6643. Min Act: -0.0000

Data Index: 11741 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7118. Min Act: -0.0000

Data Index: 631583 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6908. Min Act: -0.0000

Data Index: 1179149 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6588. Min Act: -0.0000

Data Index: 1039430 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1149887 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6470. Min Act: -0.0000

Data Index: 35132 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1163218 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6373. Min Act: -0.0000

Data Index: 16288 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6803. Min Act: -0.0000

Data Index: 341957 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6503. Min Act: -0.0000

Data Index: 665695 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6021. Min Act: -0.0000

Data Index: 118901 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6397. Min Act: -0.0000

Data Index: 410512 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.5947. Min Act: -0.0000

Data Index: 83107 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6106. Min Act: -0.0001

Data Index: 443108 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6048. Min Act: -0.0001

Data Index: 855107 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6206. Min Act: -0.0000

Data Index: 484659 (C4 (Web Text))

Max Activating Token Index: 361