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

Dataset: The Pile

Neuron 2981 in Layer 8

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: 1.9385. Min Act: -0.0000

Data Index: 660474 (The Pile)

Max Activating Token Index: 977

Text #1

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.7482. Min Act: -0.0000

Data Index: 1785380 (The Pile)

Max Activating Token Index: 503

Text #2

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6390. Min Act: -0.0000

Data Index: 256767 (The Pile)

Max Activating Token Index: 714

Text #3

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.7254. Min Act: -0.0000

Data Index: 1027996 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.8020. Min Act: -0.0000

Data Index: 576066 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6572. Min Act: -0.0000

Data Index: 566495 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6448. Min Act: -0.0000

Data Index: 766695 (The Pile)

Max Activating Token Index: 405

Text #7

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6355. Min Act: -0.0000

Data Index: 142461 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6133. Min Act: -0.0000

Data Index: 1054290 (The Pile)

Max Activating Token Index: 596

Text #9

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6922. Min Act: -0.0000

Data Index: 519466 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4884. Min Act: -0.0000

Data Index: 1185447 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5379. Min Act: -0.0000

Data Index: 1226271 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5428. Min Act: -0.0000

Data Index: 1922496 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.6183. Min Act: -0.0000

Data Index: 1091496 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4408. Min Act: -0.0000

Data Index: 538197 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5242. Min Act: -0.0000

Data Index: 1550351 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4390. Min Act: 0.0000

Data Index: 828791 (The Pile)

Max Activating Token Index: 843

Text #17

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4928. Min Act: -0.0000

Data Index: 263027 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.4124. Min Act: -0.0000

Data Index: 1680002 (The Pile)

Max Activating Token Index: 766

Text #19

Max Range: 1.9385. Min Range: -1.9385

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1536619 (The Pile)

Max Activating Token Index: 568