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

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

Neuron 384 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: 0.2841. Min Range: -0.2841

Max Act: 0.2841. Min Act: -0.0000

Data Index: 338025 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2779. Min Act: -0.0000

Data Index: 176121 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2624. Min Act: -0.0001

Data Index: 880463 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2367. Min Act: -0.0001

Data Index: 284081 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2427. Min Act: -0.0000

Data Index: 1085778 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2245. Min Act: -0.0001

Data Index: 297425 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2321. Min Act: -0.0000

Data Index: 36205 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2308. Min Act: -0.0001

Data Index: 865848 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2291. Min Act: -0.0001

Data Index: 478135 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2332. Min Act: -0.0000

Data Index: 1191373 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2210. Min Act: -0.0000

Data Index: 618447 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2314. Min Act: -0.0000

Data Index: 56072 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2164. Min Act: -0.0000

Data Index: 311041 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2138. Min Act: -0.0001

Data Index: 186167 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2029. Min Act: -0.0001

Data Index: 951246 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2129. Min Act: -0.0000

Data Index: 280011 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2085. Min Act: -0.0000

Data Index: 766505 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.1984. Min Act: -0.0000

Data Index: 829558 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.2048. Min Act: -0.0000

Data Index: 1246284 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 0.2841. Min Range: -0.2841

Max Act: 0.1968. Min Act: -0.0001

Data Index: 872212 (C4 (Web Text))

Max Activating Token Index: 680