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

Dataset: The Pile

Neuron 1373 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: 3.7755. Min Range: -3.7755

Max Act: 3.5680. Min Act: -0.0000

Data Index: 1060122 (The Pile)

Max Activating Token Index: 617

Text #1

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7425. Min Act: -0.0000

Data Index: 1272383 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7530. Min Act: -0.0000

Data Index: 567433 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7511. Min Act: -0.0000

Data Index: 1527204 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.6485. Min Act: -0.0000

Data Index: 213381 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.3041. Min Act: -0.0000

Data Index: 1507097 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.7755. Min Act: -0.0000

Data Index: 1946064 (The Pile)

Max Activating Token Index: 249

Text #7

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.0096. Min Act: -0.0000

Data Index: 846125 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 3.7755. Min Range: -3.7755

Max Act: 2.9959. Min Act: -0.0000

Data Index: 670404 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 3.7755. Min Range: -3.7755

Max Act: 2.7993. Min Act: -0.0000

Data Index: 540251 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.2269. Min Act: -0.0000

Data Index: 890514 (The Pile)

Max Activating Token Index: 372

Text #11

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.2385. Min Act: -0.0000

Data Index: 544188 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.1043. Min Act: -0.0000

Data Index: 1098676 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 3.7755. Min Range: -3.7755

Max Act: 2.9514. Min Act: -0.0000

Data Index: 1172793 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.0764. Min Act: -0.0000

Data Index: 1846817 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.1859. Min Act: -0.0000

Data Index: 1103032 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 3.7755. Min Range: -3.7755

Max Act: 2.8105. Min Act: -0.0000

Data Index: 446698 (The Pile)

Max Activating Token Index: 1015

Text #17

Max Range: 3.7755. Min Range: -3.7755

Max Act: 2.9257. Min Act: -0.0000

Data Index: 421636 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 3.7755. Min Range: -3.7755

Max Act: 3.0480. Min Act: -0.0000

Data Index: 1560207 (The Pile)

Max Activating Token Index: 30

Text #19

Max Range: 3.7755. Min Range: -3.7755

Max Act: 2.7434. Min Act: -0.0000

Data Index: 688647 (The Pile)

Max Activating Token Index: 332