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

Dataset: The Pile

Neuron 1237 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.5161. Min Act: -0.0000

Data Index: 106893 (The Pile)

Max Activating Token Index: 302

Text #1

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1250068 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1216563 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1415200 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4765. Min Act: -0.0000

Data Index: 84113 (The Pile)

Max Activating Token Index: 350

Text #5

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1325979 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1726195 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1348298 (The Pile)

Max Activating Token Index: 170

Text #8

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1925888 (The Pile)

Max Activating Token Index: 847

Text #9

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4621. Min Act: -0.0000

Data Index: 460301 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1970041 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1954420 (The Pile)

Max Activating Token Index: 169

Text #12

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4334. Min Act: -0.0000

Data Index: 448874 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4436. Min Act: -0.0000

Data Index: 1096166 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1064141 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1257242 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4345. Min Act: -0.0000

Data Index: 172563 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4335. Min Act: -0.0000

Data Index: 409039 (The Pile)

Max Activating Token Index: 415

Text #18

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4446. Min Act: -0.0000

Data Index: 793334 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 0.5161. Min Range: -0.5161

Max Act: 0.4428. Min Act: -0.0000

Data Index: 725396 (The Pile)

Max Activating Token Index: 632