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

Dataset: The Pile

Neuron 4659 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: 0.1220. Min Range: -0.1220

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1538857 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1175. Min Act: -0.0000

Data Index: 385315 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1220. Min Act: -0.0000

Data Index: 809197 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1073. Min Act: -0.0000

Data Index: 448335 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1073392 (The Pile)

Max Activating Token Index: 70

Text #5

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1032. Min Act: -0.0000

Data Index: 388445 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0999. Min Act: -0.0000

Data Index: 428485 (The Pile)

Max Activating Token Index: 488

Text #7

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0960. Min Act: -0.0000

Data Index: 708935 (The Pile)

Max Activating Token Index: 749

Text #8

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0989. Min Act: -0.0000

Data Index: 342844 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1213936 (The Pile)

Max Activating Token Index: 318

Text #10

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0877. Min Act: -0.0000

Data Index: 1917185 (The Pile)

Max Activating Token Index: 917

Text #11

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1799747 (The Pile)

Max Activating Token Index: 766

Text #12

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1248685 (The Pile)

Max Activating Token Index: 191

Text #13

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0931. Min Act: -0.0000

Data Index: 352487 (The Pile)

Max Activating Token Index: 228

Text #14

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1603707 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0928. Min Act: -0.0000

Data Index: 20035 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0939. Min Act: -0.0000

Data Index: 50884 (The Pile)

Max Activating Token Index: 194

Text #17

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1841928 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1169682 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.1220. Min Range: -0.1220

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1468736 (The Pile)

Max Activating Token Index: 974