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

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

Neuron 3800 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: 1.3327. Min Range: -1.3327

Max Act: 1.2667. Min Act: -0.0000

Data Index: 936077 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.3327. Min Act: -0.0000

Data Index: 468390 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.1198. Min Act: -0.0000

Data Index: 602298 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.1140. Min Act: -0.0000

Data Index: 1077277 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.1870. Min Act: -0.0000

Data Index: 569761 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.0900. Min Act: -0.0000

Data Index: 902497 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.0761. Min Act: -0.0000

Data Index: 654430 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9997. Min Act: -0.0000

Data Index: 446529 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9391. Min Act: -0.0000

Data Index: 429683 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.0834. Min Act: -0.0000

Data Index: 833267 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.8988. Min Act: -0.0000

Data Index: 285254 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.1127. Min Act: -0.0000

Data Index: 12236 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 1.3327. Min Range: -1.3327

Max Act: 1.0370. Min Act: -0.0000

Data Index: 167050 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1232267 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.8478. Min Act: -0.0000

Data Index: 457003 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9981. Min Act: -0.0000

Data Index: 51383 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1334404 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9418. Min Act: -0.0000

Data Index: 507405 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9650. Min Act: -0.0000

Data Index: 832918 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 1.3327. Min Range: -1.3327

Max Act: 0.9181. Min Act: -0.0000

Data Index: 340731 (C4 (Web Text))

Max Activating Token Index: 161