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

Dataset: The Pile

Neuron 4936 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: 1.8097. Min Range: -1.8097

Max Act: 1.8097. Min Act: -0.0000

Data Index: 1244486 (The Pile)

Max Activating Token Index: 340

Text #1

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.4729. Min Act: -0.0000

Data Index: 1266268 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.4717. Min Act: -0.0000

Data Index: 1645125 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.4009. Min Act: -0.0000

Data Index: 842786 (The Pile)

Max Activating Token Index: 114

Text #4

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.3876. Min Act: -0.0000

Data Index: 143145 (The Pile)

Max Activating Token Index: 336

Text #5

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2935. Min Act: -0.0000

Data Index: 1362350 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1929. Min Act: -0.0000

Data Index: 1992778 (The Pile)

Max Activating Token Index: 559

Text #7

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1422996 (The Pile)

Max Activating Token Index: 42

Text #8

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.4172. Min Act: -0.0000

Data Index: 410975 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.3167. Min Act: -0.0000

Data Index: 1984009 (The Pile)

Max Activating Token Index: 758

Text #10

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2856. Min Act: -0.0000

Data Index: 248673 (The Pile)

Max Activating Token Index: 517

Text #11

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2811. Min Act: -0.0000

Data Index: 771946 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2253. Min Act: -0.0000

Data Index: 940071 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1727. Min Act: -0.0000

Data Index: 113873 (The Pile)

Max Activating Token Index: 522

Text #14

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1752409 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1952. Min Act: -0.0000

Data Index: 1848455 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2965. Min Act: -0.0000

Data Index: 359845 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2408. Min Act: -0.0000

Data Index: 869503 (The Pile)

Max Activating Token Index: 808

Text #18

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1835. Min Act: -0.0000

Data Index: 468131 (The Pile)

Max Activating Token Index: 405

Text #19

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1390. Min Act: -0.0000

Data Index: 440184 (The Pile)

Max Activating Token Index: 33