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

Dataset: The Pile

Neuron 2803 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4974. Min Act: -0.0000

Data Index: 62163 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4265. Min Act: -0.0000

Data Index: 51967 (The Pile)

Max Activating Token Index: 109

Text #2

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1469000 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1431968 (The Pile)

Max Activating Token Index: 545

Text #4

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1068751 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1422144 (The Pile)

Max Activating Token Index: 35

Text #6

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1509897 (The Pile)

Max Activating Token Index: 195

Text #7

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4307. Min Act: -0.0000

Data Index: 71793 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1745654 (The Pile)

Max Activating Token Index: 162

Text #9

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3908. Min Act: -0.0000

Data Index: 823517 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3919. Min Act: -0.0000

Data Index: 1177971 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3537. Min Act: -0.0000

Data Index: 5325 (The Pile)

Max Activating Token Index: 965

Text #12

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1921082 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1871088 (The Pile)

Max Activating Token Index: 84

Text #14

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1175986 (The Pile)

Max Activating Token Index: 114

Text #15

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3515. Min Act: -0.0000

Data Index: 193795 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3793. Min Act: -0.0000

Data Index: 993068 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.4142. Min Act: -0.0000

Data Index: 223740 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1463430 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 0.4974. Min Range: -0.4974

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1361593 (The Pile)

Max Activating Token Index: 238