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

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

Neuron 4813 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.5353. Min Act: -0.0000

Data Index: 1473822 (Python Code)

Max Activating Token Index: 231

Text #1

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3721. Min Act: -0.0000

Data Index: 1520561 (Python Code)

Max Activating Token Index: 103

Text #2

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.7157. Min Act: -0.0000

Data Index: 1473952 (Python Code)

Max Activating Token Index: 867

Text #3

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.4367. Min Act: -0.0000

Data Index: 1466408 (Python Code)

Max Activating Token Index: 733

Text #4

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.2982. Min Act: -0.0000

Data Index: 1597654 (Python Code)

Max Activating Token Index: 126

Text #5

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3759. Min Act: -0.0000

Data Index: 1539298 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3779. Min Act: -0.0000

Data Index: 1501511 (Python Code)

Max Activating Token Index: 532

Text #7

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3386. Min Act: -0.0000

Data Index: 1503299 (Python Code)

Max Activating Token Index: 497

Text #8

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.4318. Min Act: -0.0000

Data Index: 1431100 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3122. Min Act: -0.0000

Data Index: 1617004 (Python Code)

Max Activating Token Index: 246

Text #10

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.2927. Min Act: -0.0000

Data Index: 1655187 (Python Code)

Max Activating Token Index: 297

Text #11

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.2727. Min Act: -0.0000

Data Index: 1608374 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3582. Min Act: -0.0000

Data Index: 1624531 (Python Code)

Max Activating Token Index: 187

Text #13

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.2260. Min Act: -0.0000

Data Index: 1577323 (Python Code)

Max Activating Token Index: 245

Text #14

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.2137. Min Act: -0.0000

Data Index: 1520441 (Python Code)

Max Activating Token Index: 50

Text #15

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3328. Min Act: -0.0000

Data Index: 1516582 (Python Code)

Max Activating Token Index: 77

Text #16

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.0981. Min Act: -0.0000

Data Index: 1557937 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.3129. Min Act: -0.0000

Data Index: 1508343 (Python Code)

Max Activating Token Index: 115

Text #18

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.1954. Min Act: -0.0000

Data Index: 1595234 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 2.7157. Min Range: -2.7157

Max Act: 2.1867. Min Act: -0.0000

Data Index: 1483958 (Python Code)

Max Activating Token Index: 991