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

Dataset: The Pile

Neuron 3482 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: 1.3866. Min Range: -1.3866

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1271687 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0940. Min Act: -0.0000

Data Index: 295469 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1286879 (The Pile)

Max Activating Token Index: 226

Text #3

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.1031. Min Act: -0.0000

Data Index: 549500 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0819. Min Act: -0.0000

Data Index: 523840 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8802. Min Act: -0.0000

Data Index: 303137 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.1201. Min Act: -0.0000

Data Index: 1746886 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0272. Min Act: -0.0000

Data Index: 498298 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 1.3866. Min Range: -1.3866

Max Act: 1.0405. Min Act: -0.0000

Data Index: 938142 (The Pile)

Max Activating Token Index: 208

Text #9

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9629. Min Act: -0.0000

Data Index: 373686 (The Pile)

Max Activating Token Index: 208

Text #10

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9675. Min Act: -0.0000

Data Index: 803566 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9250. Min Act: -0.0000

Data Index: 1843342 (The Pile)

Max Activating Token Index: 471

Text #12

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1922885 (The Pile)

Max Activating Token Index: 277

Text #13

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9294. Min Act: -0.0000

Data Index: 734335 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8675. Min Act: -0.0000

Data Index: 528742 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1650454 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8778. Min Act: -0.0000

Data Index: 361773 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.9096. Min Act: -0.0000

Data Index: 984443 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8320. Min Act: -0.0000

Data Index: 1517564 (The Pile)

Max Activating Token Index: 131

Text #19

Max Range: 1.3866. Min Range: -1.3866

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1937223 (The Pile)

Max Activating Token Index: 274