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

Dataset: The Pile

Neuron 4080 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: 1.0393. Min Range: -1.0393

Max Act: 1.0393. Min Act: -0.0000

Data Index: 569207 (The Pile)

Max Activating Token Index: 38

Text #1

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9524. Min Act: -0.0000

Data Index: 1650450 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1330276 (The Pile)

Max Activating Token Index: 41

Text #3

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9495. Min Act: -0.0000

Data Index: 775453 (The Pile)

Max Activating Token Index: 44

Text #4

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9145. Min Act: -0.0000

Data Index: 683706 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9777. Min Act: -0.0000

Data Index: 110725 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8938. Min Act: -0.0000

Data Index: 536129 (The Pile)

Max Activating Token Index: 31

Text #7

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9236. Min Act: -0.0000

Data Index: 686456 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1108518 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1118678 (The Pile)

Max Activating Token Index: 43

Text #10

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8290. Min Act: -0.0000

Data Index: 209940 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1868928 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1337102 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8776. Min Act: -0.0000

Data Index: 21990 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1269493 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.9142. Min Act: -0.0000

Data Index: 1607454 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1292140 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8288. Min Act: -0.0000

Data Index: 1750963 (The Pile)

Max Activating Token Index: 21

Text #18

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.7977. Min Act: -0.0000

Data Index: 658262 (The Pile)

Max Activating Token Index: 565

Text #19

Max Range: 1.0393. Min Range: -1.0393

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1942351 (The Pile)

Max Activating Token Index: 52