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

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

Neuron 3893 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.6858. Min Act: -0.0002

Data Index: 1507771 (Python Code)

Max Activating Token Index: 336

Text #1

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.1232. Min Act: -0.0002

Data Index: 1423071 (Python Code)

Max Activating Token Index: 214

Text #2

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.1389. Min Act: -0.0002

Data Index: 1491812 (Python Code)

Max Activating Token Index: 8

Text #3

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.1301. Min Act: -0.0002

Data Index: 1634612 (Python Code)

Max Activating Token Index: 840

Text #4

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.0543. Min Act: -0.0002

Data Index: 1521968 (Python Code)

Max Activating Token Index: 63

Text #5

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.0452. Min Act: -0.0002

Data Index: 1403461 (Python Code)

Max Activating Token Index: 228

Text #6

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.0101. Min Act: -0.0002

Data Index: 1371685 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.0046. Min Act: -0.0002

Data Index: 1620426 (Python Code)

Max Activating Token Index: 279

Text #8

Max Range: 11.6858. Min Range: -11.6858

Max Act: 11.0675. Min Act: -0.0002

Data Index: 1626258 (Python Code)

Max Activating Token Index: 548

Text #9

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.9268. Min Act: -0.0002

Data Index: 1493201 (Python Code)

Max Activating Token Index: 777

Text #10

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.9239. Min Act: -0.0002

Data Index: 1425192 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.9724. Min Act: -0.0002

Data Index: 1448116 (Python Code)

Max Activating Token Index: 92

Text #12

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.8835. Min Act: -0.0002

Data Index: 1606754 (Python Code)

Max Activating Token Index: 73

Text #13

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.8782. Min Act: -0.0002

Data Index: 1563735 (Python Code)

Max Activating Token Index: 240

Text #14

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.7936. Min Act: -0.0002

Data Index: 1375598 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.8552. Min Act: -0.0002

Data Index: 1506524 (Python Code)

Max Activating Token Index: 369

Text #16

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.7650. Min Act: -0.0002

Data Index: 1395367 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.7486. Min Act: -0.0002

Data Index: 727367 (C4 (Web Text))

Max Activating Token Index: 8

Text #18

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.7240. Min Act: -0.0002

Data Index: 1364809 (Python Code)

Max Activating Token Index: 233

Text #19

Max Range: 11.6858. Min Range: -11.6858

Max Act: 10.8129. Min Act: -0.0002

Data Index: 1429088 (Python Code)

Max Activating Token Index: 836