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

Dataset: The Pile

Neuron 3387 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: 0.7277. Min Range: -0.7277

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1450228 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.7145. Min Act: -0.0000

Data Index: 83393 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6924. Min Act: -0.0000

Data Index: 1114136 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1796065 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1287158 (The Pile)

Max Activating Token Index: 135

Text #5

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6701. Min Act: -0.0000

Data Index: 1509708 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6907. Min Act: -0.0000

Data Index: 176289 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6216. Min Act: -0.0000

Data Index: 829305 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6609. Min Act: -0.0000

Data Index: 254444 (The Pile)

Max Activating Token Index: 43

Text #9

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6175. Min Act: -0.0000

Data Index: 754702 (The Pile)

Max Activating Token Index: 164

Text #10

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6341. Min Act: -0.0000

Data Index: 149510 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6568. Min Act: -0.0000

Data Index: 1560015 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1192311 (The Pile)

Max Activating Token Index: 739

Text #13

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6200. Min Act: -0.0000

Data Index: 1250447 (The Pile)

Max Activating Token Index: 37

Text #14

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.5943. Min Act: -0.0000

Data Index: 938205 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6324. Min Act: -0.0000

Data Index: 714425 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6312. Min Act: -0.0000

Data Index: 1878990 (The Pile)

Max Activating Token Index: 48

Text #17

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1163200 (The Pile)

Max Activating Token Index: 62

Text #18

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1206091 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.7277. Min Range: -0.7277

Max Act: 0.6299. Min Act: -0.0000

Data Index: 712135 (The Pile)

Max Activating Token Index: 42