Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0856. Min Range: -1.0856

Max Act: 1.0856. Min Act: -0.0000

Data Index: 696260 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9396. Min Act: -0.0000

Data Index: 1668621 (The Pile)

Max Activating Token Index: 187

Text #2

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9331. Min Act: -0.0000

Data Index: 1334470 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8319. Min Act: -0.0000

Data Index: 468669 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1654042 (The Pile)

Max Activating Token Index: 79

Text #5

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8721. Min Act: -0.0000

Data Index: 90302 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.9157. Min Act: -0.0000

Data Index: 1649038 (The Pile)

Max Activating Token Index: 65

Text #7

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8996. Min Act: -0.0000

Data Index: 935606 (The Pile)

Max Activating Token Index: 77

Text #8

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1985768 (The Pile)

Max Activating Token Index: 257

Text #9

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8890. Min Act: -0.0001

Data Index: 1015959 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1184126 (The Pile)

Max Activating Token Index: 985

Text #11

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8392. Min Act: -0.0000

Data Index: 702570 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1194174 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8936. Min Act: -0.0000

Data Index: 216806 (The Pile)

Max Activating Token Index: 257

Text #14

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8953. Min Act: -0.0000

Data Index: 60363 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8122. Min Act: -0.0000

Data Index: 494637 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8407. Min Act: -0.0000

Data Index: 1352275 (The Pile)

Max Activating Token Index: 331

Text #17

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8881. Min Act: -0.0000

Data Index: 509853 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1347737 (The Pile)

Max Activating Token Index: 180

Text #19

Max Range: 1.0856. Min Range: -1.0856

Max Act: 0.7868. Min Act: -0.0000

Data Index: 22622 (The Pile)

Max Activating Token Index: 809