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

Dataset: The Pile

Neuron 4366 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.8482. Min Act: -0.0000

Data Index: 566461 (The Pile)

Max Activating Token Index: 813

Text #1

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.8227. Min Act: -0.0000

Data Index: 999674 (The Pile)

Max Activating Token Index: 128

Text #2

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.8316. Min Act: 0.0000

Data Index: 764718 (The Pile)

Max Activating Token Index: 908

Text #3

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.8358. Min Act: -0.0000

Data Index: 937997 (The Pile)

Max Activating Token Index: 396

Text #4

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7669. Min Act: -0.0000

Data Index: 136220 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1267546 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7033. Min Act: -0.0000

Data Index: 1047489 (The Pile)

Max Activating Token Index: 582

Text #7

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6966. Min Act: 0.0000

Data Index: 1907964 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1082944 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1635995 (The Pile)

Max Activating Token Index: 340

Text #10

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1695653 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7065. Min Act: -0.0000

Data Index: 469068 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6801. Min Act: -0.0000

Data Index: 533257 (The Pile)

Max Activating Token Index: 943

Text #13

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6987. Min Act: 0.0000

Data Index: 1082517 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6398. Min Act: -0.0000

Data Index: 244568 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1915172 (The Pile)

Max Activating Token Index: 461

Text #16

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.7046. Min Act: -0.0000

Data Index: 1078095 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6379. Min Act: -0.0000

Data Index: 807150 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6580. Min Act: -0.0000

Data Index: 412686 (The Pile)

Max Activating Token Index: 328

Text #19

Max Range: 0.8482. Min Range: -0.8482

Max Act: 0.6453. Min Act: -0.0000

Data Index: 837356 (The Pile)

Max Activating Token Index: 747