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

Dataset: The Pile

Neuron 681 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0000

Data Index: 1466239 (The Pile)

Max Activating Token Index: 79

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1531232 (The Pile)

Max Activating Token Index: 460

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0371. Min Act: -0.0000

Data Index: 377316 (The Pile)

Max Activating Token Index: 189

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0386. Min Act: -0.0000

Data Index: 891518 (The Pile)

Max Activating Token Index: 213

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1687803 (The Pile)

Max Activating Token Index: 57

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0368. Min Act: -0.0000

Data Index: 34619 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0362. Min Act: -0.0000

Data Index: 1357378 (The Pile)

Max Activating Token Index: 203

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0359. Min Act: -0.0000

Data Index: 1113218 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0355. Min Act: -0.0000

Data Index: 1716174 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1117747 (The Pile)

Max Activating Token Index: 194

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0363. Min Act: -0.0000

Data Index: 1302585 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0358. Min Act: -0.0000

Data Index: 557271 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0317. Min Act: -0.0000

Data Index: 1691184 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1437902 (The Pile)

Max Activating Token Index: 188

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0328. Min Act: -0.0000

Data Index: 230202 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0313. Min Act: -0.0000

Data Index: 312890 (The Pile)

Max Activating Token Index: 120

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1708120 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0319. Min Act: -0.0000

Data Index: 115790 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0320. Min Act: -0.0000

Data Index: 1406912 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0306. Min Act: -0.0000

Data Index: 1239075 (The Pile)

Max Activating Token Index: 158