Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4821 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1443179 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1628665 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1507828 (Python Code)

Max Activating Token Index: 754

Text #3

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1588374 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1498680 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1498351 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1532150 (Python Code)

Max Activating Token Index: 583

Text #7

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1534252 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1391310 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0267. Min Act: -0.0002

Data Index: 1636995 (Python Code)

Max Activating Token Index: 86

Text #10

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0266. Min Act: -0.0003

Data Index: 1414228 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0264. Min Act: -0.0003

Data Index: 1565665 (Python Code)

Max Activating Token Index: 544

Text #12

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1458407 (Python Code)

Max Activating Token Index: 763

Text #13

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1635228 (Python Code)

Max Activating Token Index: 157

Text #14

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0263. Min Act: -0.0003

Data Index: 1521563 (Python Code)

Max Activating Token Index: 359

Text #15

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1457578 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1535552 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1513993 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0255. Min Act: -0.0003

Data Index: 1454092 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 0.0432. Min Range: -0.0432

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1580215 (Python Code)

Max Activating Token Index: 155