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

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

Neuron 5934 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.7553. Min Act: -0.0000

Data Index: 1419158 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.3508. Min Act: -0.0000

Data Index: 1349342 (C4 (Web Text))

Max Activating Token Index: 598

Text #2

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.2135. Min Act: -0.0000

Data Index: 1654682 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0768. Min Act: -0.0000

Data Index: 1559871 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0447. Min Act: -0.0000

Data Index: 1521571 (Python Code)

Max Activating Token Index: 923

Text #5

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.1186. Min Act: -0.0000

Data Index: 1613727 (Python Code)

Max Activating Token Index: 517

Text #6

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0001. Min Act: -0.0000

Data Index: 1414226 (Python Code)

Max Activating Token Index: 119

Text #7

Max Range: 2.7553. Min Range: -2.7553

Max Act: 1.9903. Min Act: -0.0000

Data Index: 1467007 (Python Code)

Max Activating Token Index: 208

Text #8

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.1106. Min Act: -0.0000

Data Index: 1377928 (Python Code)

Max Activating Token Index: 219

Text #9

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.1084. Min Act: -0.0000

Data Index: 1564623 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0934. Min Act: -0.0000

Data Index: 1620836 (Python Code)

Max Activating Token Index: 105

Text #11

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0862. Min Act: -0.0000

Data Index: 1468179 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 2.7553. Min Range: -2.7553

Max Act: 1.8715. Min Act: -0.0000

Data Index: 1390553 (Python Code)

Max Activating Token Index: 264

Text #13

Max Range: 2.7553. Min Range: -2.7553

Max Act: 1.9838. Min Act: -0.0000

Data Index: 1649216 (Python Code)

Max Activating Token Index: 314

Text #14

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0938. Min Act: -0.0000

Data Index: 1436906 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0807. Min Act: -0.0000

Data Index: 1517239 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0838. Min Act: -0.0000

Data Index: 1034936 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0670. Min Act: -0.0000

Data Index: 1517082 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0791. Min Act: -0.0000

Data Index: 1613676 (Python Code)

Max Activating Token Index: 193

Text #19

Max Range: 2.7553. Min Range: -2.7553

Max Act: 2.0681. Min Act: -0.0000

Data Index: 1533240 (Python Code)

Max Activating Token Index: 535