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

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

Neuron 3065 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0197. Min Act: -0.0003

Data Index: 961151 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1437319 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1557716 (Python Code)

Max Activating Token Index: 5

Text #3

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1515688 (Python Code)

Max Activating Token Index: 129

Text #4

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1400792 (Python Code)

Max Activating Token Index: 85

Text #5

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1361191 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1393021 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1538833 (Python Code)

Max Activating Token Index: 5

Text #8

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1644868 (Python Code)

Max Activating Token Index: 649

Text #9

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1432581 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1568059 (Python Code)

Max Activating Token Index: 217

Text #11

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1556148 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1376518 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1487729 (Python Code)

Max Activating Token Index: 64

Text #14

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1582716 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1467384 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1648530 (Python Code)

Max Activating Token Index: 106

Text #17

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1610053 (Python Code)

Max Activating Token Index: 789

Text #18

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1591017 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.0197. Min Range: -0.0197

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1369776 (Python Code)

Max Activating Token Index: 12