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

Dataset: The Pile

Neuron 1013 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 12.1157. Min Range: -12.1157

Max Act: 12.1157. Min Act: -0.0000

Data Index: 1649500 (The Pile)

Max Activating Token Index: 91

Text #1

Max Range: 12.1157. Min Range: -12.1157

Max Act: 12.0274. Min Act: -0.0000

Data Index: 985455 (The Pile)

Max Activating Token Index: 87

Text #2

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.5951. Min Act: -0.0000

Data Index: 1080305 (The Pile)

Max Activating Token Index: 153

Text #3

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.9389. Min Act: -0.0000

Data Index: 164939 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.5364. Min Act: -0.0000

Data Index: 926045 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.6096. Min Act: -0.0000

Data Index: 482584 (The Pile)

Max Activating Token Index: 201

Text #6

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7938. Min Act: -0.0000

Data Index: 93529 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7340. Min Act: -0.0000

Data Index: 599395 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7446. Min Act: -0.0000

Data Index: 23472 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.8437. Min Act: -0.0000

Data Index: 1488809 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.5300. Min Act: -0.0000

Data Index: 372465 (The Pile)

Max Activating Token Index: 120

Text #11

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.6291. Min Act: -0.0000

Data Index: 1872374 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7279. Min Act: -0.0000

Data Index: 1833430 (The Pile)

Max Activating Token Index: 92

Text #13

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7336. Min Act: -0.0000

Data Index: 726518 (The Pile)

Max Activating Token Index: 135

Text #14

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.5327. Min Act: -0.0000

Data Index: 1331790 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.8281. Min Act: -0.0000

Data Index: 439341 (The Pile)

Max Activating Token Index: 112

Text #16

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.5612. Min Act: -0.0000

Data Index: 1491629 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7527. Min Act: -0.0000

Data Index: 1576860 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.7413. Min Act: -0.0000

Data Index: 1031730 (The Pile)

Max Activating Token Index: 77

Text #19

Max Range: 12.1157. Min Range: -12.1157

Max Act: 11.4224. Min Act: -0.0000

Data Index: 207818 (The Pile)

Max Activating Token Index: 75