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

Dataset: The Pile

Neuron 4178 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9769. Min Act: -0.0000

Data Index: 898205 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9945. Min Act: -0.0000

Data Index: 727294 (The Pile)

Max Activating Token Index: 511

Text #2

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9013. Min Act: -0.0000

Data Index: 312507 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9324. Min Act: -0.0000

Data Index: 808870 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1227458 (The Pile)

Max Activating Token Index: 588

Text #5

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1923308 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1796685 (The Pile)

Max Activating Token Index: 912

Text #7

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1782106 (The Pile)

Max Activating Token Index: 197

Text #8

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8395. Min Act: -0.0000

Data Index: 1286278 (The Pile)

Max Activating Token Index: 142

Text #9

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8649. Min Act: -0.0000

Data Index: 937065 (The Pile)

Max Activating Token Index: 732

Text #10

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1976177 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8336. Min Act: -0.0000

Data Index: 194630 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8415. Min Act: -0.0000

Data Index: 771403 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8298. Min Act: -0.0000

Data Index: 1067821 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8021. Min Act: -0.0000

Data Index: 798315 (The Pile)

Max Activating Token Index: 387

Text #15

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1137399 (The Pile)

Max Activating Token Index: 217

Text #16

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8108. Min Act: -0.0000

Data Index: 498038 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8154. Min Act: -0.0000

Data Index: 775312 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1020174 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7824. Min Act: -0.0000

Data Index: 298188 (The Pile)

Max Activating Token Index: 444