Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2395 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.6084. Min Act: -0.0000

Data Index: 1205231 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.5038. Min Act: -0.0000

Data Index: 851941 (The Pile)

Max Activating Token Index: 260

Text #2

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4548. Min Act: -0.0000

Data Index: 1999095 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.3764. Min Act: -0.0000

Data Index: 1739727 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.5267. Min Act: -0.0000

Data Index: 1558988 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1945820 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.3366. Min Act: -0.0000

Data Index: 230170 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1030156 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4981. Min Act: -0.0000

Data Index: 287209 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4540. Min Act: -0.0000

Data Index: 1424327 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4561. Min Act: -0.0000

Data Index: 740498 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.3592. Min Act: -0.0000

Data Index: 1294435 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1034347 (The Pile)

Max Activating Token Index: 222

Text #13

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4677. Min Act: -0.0000

Data Index: 1958940 (The Pile)

Max Activating Token Index: 193

Text #14

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4344. Min Act: -0.0000

Data Index: 863027 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4267. Min Act: -0.0000

Data Index: 1857379 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4319. Min Act: -0.0000

Data Index: 1083667 (The Pile)

Max Activating Token Index: 270

Text #17

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4221. Min Act: -0.0000

Data Index: 120899 (The Pile)

Max Activating Token Index: 313

Text #18

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4241. Min Act: -0.0000

Data Index: 234372 (The Pile)

Max Activating Token Index: 252

Text #19

Max Range: 1.6084. Min Range: -1.6084

Max Act: 1.4548. Min Act: -0.0000

Data Index: 514040 (The Pile)

Max Activating Token Index: 760