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

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

Neuron 5918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.5643. Min Act: -0.0000

Data Index: 948148 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.7215. Min Act: -0.0000

Data Index: 1118110 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.5653. Min Act: -0.0000

Data Index: 755630 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.5397. Min Act: -0.0000

Data Index: 329099 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.5515. Min Act: -0.0000

Data Index: 765237 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.2773. Min Act: -0.0000

Data Index: 155708 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.4765. Min Act: -0.0000

Data Index: 706516 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.4476. Min Act: -0.0000

Data Index: 73495 (C4 (Web Text))

Max Activating Token Index: 354

Text #8

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.4087. Min Act: -0.0000

Data Index: 1320353 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.1490. Min Act: -0.0000

Data Index: 722787 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.2894. Min Act: -0.0000

Data Index: 475337 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.2907. Min Act: -0.0000

Data Index: 1033840 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.3001. Min Act: -0.0000

Data Index: 871981 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.4471. Min Act: -0.0000

Data Index: 308430 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.4130. Min Act: -0.0000

Data Index: 1091643 (C4 (Web Text))

Max Activating Token Index: 1004

Text #15

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.1995. Min Act: -0.0000

Data Index: 1319259 (C4 (Web Text))

Max Activating Token Index: 810

Text #16

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.0147. Min Act: -0.0000

Data Index: 1221324 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.1648. Min Act: -0.0000

Data Index: 546811 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.0178. Min Act: -0.0000

Data Index: 98191 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 4.7215. Min Range: -4.7215

Max Act: 4.0131. Min Act: -0.0000

Data Index: 190783 (C4 (Web Text))

Max Activating Token Index: 176