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

Dataset: The Pile

Neuron 1287 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: 1.9385. Min Range: -1.9385

Max Act: 1.7942. Min Act: -0.0000

Data Index: 651889 (The Pile)

Max Activating Token Index: 665

Text #1

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.9385. Min Act: -0.0000

Data Index: 210722 (The Pile)

Max Activating Token Index: 763

Text #2

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.7415. Min Act: -0.0000

Data Index: 855550 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6236. Min Act: -0.0000

Data Index: 1717108 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6886. Min Act: -0.0000

Data Index: 54013 (The Pile)

Max Activating Token Index: 932

Text #5

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5561. Min Act: -0.0000

Data Index: 798439 (The Pile)

Max Activating Token Index: 625

Text #6

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.3932. Min Act: -0.0000

Data Index: 297187 (The Pile)

Max Activating Token Index: 207

Text #7

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6299. Min Act: -0.0000

Data Index: 546184 (The Pile)

Max Activating Token Index: 204

Text #8

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6227. Min Act: -0.0000

Data Index: 571226 (The Pile)

Max Activating Token Index: 438

Text #9

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5292. Min Act: -0.0000

Data Index: 1176277 (The Pile)

Max Activating Token Index: 896

Text #10

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6064. Min Act: -0.0000

Data Index: 492814 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4856. Min Act: -0.0000

Data Index: 918800 (The Pile)

Max Activating Token Index: 778

Text #12

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5847. Min Act: -0.0000

Data Index: 1126030 (The Pile)

Max Activating Token Index: 647

Text #13

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4962. Min Act: -0.0000

Data Index: 1182905 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5345. Min Act: -0.0000

Data Index: 662709 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4842. Min Act: -0.0000

Data Index: 348778 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4044. Min Act: -0.0000

Data Index: 7495 (The Pile)

Max Activating Token Index: 470

Text #17

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5705. Min Act: -0.0000

Data Index: 1154955 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1673526 (The Pile)

Max Activating Token Index: 647

Text #19

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5417. Min Act: -0.0000

Data Index: 1291230 (The Pile)

Max Activating Token Index: 442