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

Dataset: The Pile

Neuron 4669 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.3538. Min Act: -0.0000

Data Index: 1338137 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.3490. Min Act: -0.0000

Data Index: 1523887 (The Pile)

Max Activating Token Index: 152

Text #2

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.2506. Min Act: -0.0000

Data Index: 442070 (The Pile)

Max Activating Token Index: 369

Text #3

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.2319. Min Act: -0.0000

Data Index: 822294 (The Pile)

Max Activating Token Index: 781

Text #4

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.1645. Min Act: -0.0000

Data Index: 877403 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.1113. Min Act: -0.0000

Data Index: 430003 (The Pile)

Max Activating Token Index: 394

Text #6

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.1139. Min Act: -0.0000

Data Index: 107125 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.1304. Min Act: -0.0000

Data Index: 398194 (The Pile)

Max Activating Token Index: 760

Text #8

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0334. Min Act: -0.0000

Data Index: 65774 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0118. Min Act: -0.0000

Data Index: 365084 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0083. Min Act: -0.0000

Data Index: 356340 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1745649 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1418150 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1967853 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9638. Min Act: -0.0000

Data Index: 795014 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9440. Min Act: -0.0000

Data Index: 1513262 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9297. Min Act: -0.0000

Data Index: 335800 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 1.3538. Min Range: -1.3538

Max Act: 1.0325. Min Act: -0.0000

Data Index: 870811 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.8423. Min Act: -0.0000

Data Index: 620201 (The Pile)

Max Activating Token Index: 159

Text #19

Max Range: 1.3538. Min Range: -1.3538

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1941535 (The Pile)

Max Activating Token Index: 87