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

Dataset: The Pile

Neuron 108 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: 0.3379. Min Range: -0.3379

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1333370 (The Pile)

Max Activating Token Index: 276

Text #1

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1584638 (The Pile)

Max Activating Token Index: 470

Text #2

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2602. Min Act: -0.0000

Data Index: 522457 (The Pile)

Max Activating Token Index: 346

Text #3

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1680555 (The Pile)

Max Activating Token Index: 371

Text #4

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2410. Min Act: -0.0000

Data Index: 601340 (The Pile)

Max Activating Token Index: 410

Text #5

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2287. Min Act: -0.0000

Data Index: 384580 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1283543 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1338856 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2192. Min Act: -0.0000

Data Index: 72888 (The Pile)

Max Activating Token Index: 503

Text #9

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2246. Min Act: -0.0000

Data Index: 1639744 (The Pile)

Max Activating Token Index: 175

Text #10

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2106. Min Act: -0.0000

Data Index: 477695 (The Pile)

Max Activating Token Index: 195

Text #11

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1255632 (The Pile)

Max Activating Token Index: 297

Text #12

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1924546 (The Pile)

Max Activating Token Index: 23

Text #13

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2149. Min Act: -0.0000

Data Index: 66236 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1718959 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2054. Min Act: -0.0000

Data Index: 221812 (The Pile)

Max Activating Token Index: 540

Text #16

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2104. Min Act: -0.0000

Data Index: 68911 (The Pile)

Max Activating Token Index: 496

Text #17

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2138. Min Act: -0.0000

Data Index: 465215 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.2240. Min Act: -0.0000

Data Index: 667089 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 0.3379. Min Range: -0.3379

Max Act: 0.1990. Min Act: -0.0000

Data Index: 743212 (The Pile)

Max Activating Token Index: 381