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

Dataset: The Pile

Neuron 4671 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.8133. Min Act: -0.0000

Data Index: 303263 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.8044. Min Act: -0.0000

Data Index: 421798 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7203. Min Act: -0.0000

Data Index: 679461 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7092. Min Act: -0.0000

Data Index: 772970 (The Pile)

Max Activating Token Index: 257

Text #4

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.6590. Min Act: -0.0000

Data Index: 300124 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1831370 (The Pile)

Max Activating Token Index: 864

Text #6

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1004809 (The Pile)

Max Activating Token Index: 820

Text #7

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5678. Min Act: -0.0000

Data Index: 284100 (The Pile)

Max Activating Token Index: 121

Text #8

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1230322 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5668. Min Act: -0.0000

Data Index: 535311 (The Pile)

Max Activating Token Index: 1011

Text #10

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5368. Min Act: -0.0000

Data Index: 1684130 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5255. Min Act: -0.0000

Data Index: 1966749 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5404. Min Act: -0.0000

Data Index: 58941 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5373. Min Act: -0.0000

Data Index: 540752 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5363. Min Act: -0.0000

Data Index: 832896 (The Pile)

Max Activating Token Index: 355

Text #15

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1975853 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5327. Min Act: -0.0000

Data Index: 541178 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5089. Min Act: -0.0000

Data Index: 905517 (The Pile)

Max Activating Token Index: 205

Text #18

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5232. Min Act: -0.0000

Data Index: 695769 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 0.8133. Min Range: -0.8133

Max Act: 0.5332. Min Act: -0.0000

Data Index: 444219 (The Pile)

Max Activating Token Index: 936