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

Dataset: The Pile

Neuron 3178 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: 0.5198. Min Range: -0.5198

Max Act: 0.5198. Min Act: -0.0000

Data Index: 763716 (The Pile)

Max Activating Token Index: 374

Text #1

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.5008. Min Act: -0.0000

Data Index: 1894936 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4359. Min Act: -0.0000

Data Index: 245050 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1010216 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1184714 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4512. Min Act: -0.0000

Data Index: 766507 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4458. Min Act: -0.0000

Data Index: 377939 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.4382. Min Act: -0.0000

Data Index: 1425370 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1799211 (The Pile)

Max Activating Token Index: 343

Text #9

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3868. Min Act: -0.0000

Data Index: 8696 (The Pile)

Max Activating Token Index: 419

Text #10

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3631. Min Act: -0.0000

Data Index: 55777 (The Pile)

Max Activating Token Index: 180

Text #11

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1162121 (The Pile)

Max Activating Token Index: 534

Text #12

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3692. Min Act: -0.0000

Data Index: 1557348 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1227811 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3586. Min Act: -0.0000

Data Index: 1570425 (The Pile)

Max Activating Token Index: 464

Text #15

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3344. Min Act: -0.0000

Data Index: 611505 (The Pile)

Max Activating Token Index: 863

Text #16

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1604023 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3281. Min Act: -0.0000

Data Index: 1703170 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3449. Min Act: -0.0000

Data Index: 618151 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.5198. Min Range: -0.5198

Max Act: 0.3434. Min Act: -0.0000

Data Index: 460188 (The Pile)

Max Activating Token Index: 302