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

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

Neuron 1508 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.7374. Min Act: -0.0000

Data Index: 1538312 (Python Code)

Max Activating Token Index: 72

Text #1

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5528. Min Act: -0.0000

Data Index: 1651335 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.7549. Min Act: -0.0000

Data Index: 1531922 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.7274. Min Act: -0.0000

Data Index: 1533702 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5756. Min Act: -0.0000

Data Index: 1616294 (Python Code)

Max Activating Token Index: 220

Text #5

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.8215. Min Act: -0.0000

Data Index: 1544710 (Python Code)

Max Activating Token Index: 66

Text #6

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5139. Min Act: -0.0000

Data Index: 1559048 (Python Code)

Max Activating Token Index: 322

Text #7

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5109. Min Act: -0.0000

Data Index: 1538430 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.6434. Min Act: -0.0000

Data Index: 1419191 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.8995. Min Act: -0.0000

Data Index: 1591273 (Python Code)

Max Activating Token Index: 729

Text #10

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1622795 (Python Code)

Max Activating Token Index: 983

Text #11

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.3925. Min Act: -0.0000

Data Index: 1438457 (Python Code)

Max Activating Token Index: 605

Text #12

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5213. Min Act: -0.0000

Data Index: 1656291 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.5262. Min Act: -0.0000

Data Index: 1503932 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.6060. Min Act: -0.0000

Data Index: 1602528 (Python Code)

Max Activating Token Index: 753

Text #15

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.3048. Min Act: -0.0000

Data Index: 1501988 (Python Code)

Max Activating Token Index: 46

Text #16

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.4297. Min Act: -0.0000

Data Index: 1499338 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.4241. Min Act: -0.0000

Data Index: 1468697 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.4251. Min Act: -0.0000

Data Index: 1567518 (Python Code)

Max Activating Token Index: 191

Text #19

Max Range: 2.8995. Min Range: -2.8995

Max Act: 2.2842. Min Act: -0.0000

Data Index: 1534436 (Python Code)

Max Activating Token Index: 119