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

Dataset: The Pile

Neuron 3646 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1041196 (The Pile)

Max Activating Token Index: 28

Text #1

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1118. Min Act: -0.0000

Data Index: 1965808 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1226. Min Act: -0.0000

Data Index: 1818413 (The Pile)

Max Activating Token Index: 383

Text #3

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1071484 (The Pile)

Max Activating Token Index: 124

Text #4

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0914. Min Act: -0.0000

Data Index: 1096983 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0902. Min Act: -0.0000

Data Index: 1075691 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1922946 (The Pile)

Max Activating Token Index: 668

Text #7

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0903. Min Act: -0.0000

Data Index: 684112 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.1040. Min Act: -0.0000

Data Index: 1120102 (The Pile)

Max Activating Token Index: 815

Text #9

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1259339 (The Pile)

Max Activating Token Index: 75

Text #10

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0945. Min Act: -0.0000

Data Index: 131838 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0877. Min Act: -0.0000

Data Index: 353029 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1414409 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0834. Min Act: -0.0000

Data Index: 228181 (The Pile)

Max Activating Token Index: 93

Text #14

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0779. Min Act: -0.0000

Data Index: 907728 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1057849 (The Pile)

Max Activating Token Index: 765

Text #16

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0932. Min Act: -0.0000

Data Index: 336947 (The Pile)

Max Activating Token Index: 576

Text #17

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1008657 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0894. Min Act: -0.0000

Data Index: 987399 (The Pile)

Max Activating Token Index: 545

Text #19

Max Range: 0.1256. Min Range: -0.1256

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1875291 (The Pile)

Max Activating Token Index: 599