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

Dataset: The Pile

Neuron 1120 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1231855 (The Pile)

Max Activating Token Index: 516

Text #1

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1600878 (The Pile)

Max Activating Token Index: 103

Text #2

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1562093 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1671281 (The Pile)

Max Activating Token Index: 60

Text #4

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7346. Min Act: -0.0000

Data Index: 1801590 (The Pile)

Max Activating Token Index: 187

Text #5

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6620. Min Act: -0.0000

Data Index: 828289 (The Pile)

Max Activating Token Index: 832

Text #6

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1194072 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7006. Min Act: -0.0000

Data Index: 150073 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6685. Min Act: -0.0000

Data Index: 519878 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6664. Min Act: -0.0000

Data Index: 720069 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6374. Min Act: -0.0000

Data Index: 1108553 (The Pile)

Max Activating Token Index: 566

Text #11

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1207804 (The Pile)

Max Activating Token Index: 147

Text #12

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1613857 (The Pile)

Max Activating Token Index: 335

Text #13

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6415. Min Act: -0.0000

Data Index: 694077 (The Pile)

Max Activating Token Index: 926

Text #14

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6440. Min Act: -0.0000

Data Index: 549955 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.7233. Min Act: -0.0000

Data Index: 163117 (The Pile)

Max Activating Token Index: 919

Text #16

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1075847 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6197. Min Act: -0.0000

Data Index: 882421 (The Pile)

Max Activating Token Index: 794

Text #18

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6344. Min Act: -0.0000

Data Index: 910434 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 0.7346. Min Range: -0.7346

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1372646 (The Pile)

Max Activating Token Index: 422