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

Dataset: The Pile

Neuron 3442 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1517007 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2996. Min Act: -0.0000

Data Index: 741402 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2661. Min Act: -0.0000

Data Index: 750779 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2365. Min Act: -0.0000

Data Index: 11368 (The Pile)

Max Activating Token Index: 211

Text #4

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1401530 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2253. Min Act: -0.0000

Data Index: 690138 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2273. Min Act: -0.0000

Data Index: 297084 (The Pile)

Max Activating Token Index: 107

Text #7

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2237. Min Act: -0.0000

Data Index: 673428 (The Pile)

Max Activating Token Index: 161

Text #8

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1537919 (The Pile)

Max Activating Token Index: 199

Text #9

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1013860 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2246. Min Act: -0.0000

Data Index: 170024 (The Pile)

Max Activating Token Index: 615

Text #11

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2172. Min Act: -0.0000

Data Index: 258013 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2105. Min Act: -0.0000

Data Index: 886633 (The Pile)

Max Activating Token Index: 122

Text #13

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2096. Min Act: -0.0000

Data Index: 92257 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2082. Min Act: -0.0000

Data Index: 106780 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1507339 (The Pile)

Max Activating Token Index: 433

Text #16

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2074. Min Act: -0.0000

Data Index: 739689 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2173. Min Act: -0.0000

Data Index: 631528 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1966171 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 0.2996. Min Range: -0.2996

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1148283 (The Pile)

Max Activating Token Index: 405