Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1712 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0006

Data Index: 1232390 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0180. Min Act: -0.0006

Data Index: 177330 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0180. Min Act: -0.0006

Data Index: 271579 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0179. Min Act: -0.0005

Data Index: 906539 (C4 (Web Text))

Max Activating Token Index: 135

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1426894 (Python Code)

Max Activating Token Index: 850

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0182. Min Act: -0.0006

Data Index: 136754 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0181. Min Act: -0.0006

Data Index: 223277 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1510772 (Python Code)

Max Activating Token Index: 722

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0006

Data Index: 439752 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0006

Data Index: 878515 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0178. Min Act: -0.0005

Data Index: 487759 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0172. Min Act: -0.0006

Data Index: 924650 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0174. Min Act: -0.0005

Data Index: 1512210 (Python Code)

Max Activating Token Index: 284

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0171. Min Act: -0.0006

Data Index: 981791 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0175. Min Act: -0.0006

Data Index: 248268 (C4 (Web Text))

Max Activating Token Index: 997

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0006

Data Index: 237838 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0164. Min Act: -0.0006

Data Index: 771489 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0168. Min Act: -0.0006

Data Index: 169350 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0169. Min Act: -0.0005

Data Index: 1571273 (Python Code)

Max Activating Token Index: 34

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0168. Min Act: -0.0005

Data Index: 448952 (C4 (Web Text))

Max Activating Token Index: 451