Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 123 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7614. Min Act: -0.0000

Data Index: 1264873 (The Pile)

Max Activating Token Index: 791

Text #1

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1695224 (The Pile)

Max Activating Token Index: 698

Text #2

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7822. Min Act: -0.0000

Data Index: 1031032 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7578. Min Act: -0.0000

Data Index: 836706 (The Pile)

Max Activating Token Index: 192

Text #4

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1595283 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7417. Min Act: -0.0000

Data Index: 287240 (The Pile)

Max Activating Token Index: 643

Text #6

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7420. Min Act: -0.0000

Data Index: 547892 (The Pile)

Max Activating Token Index: 331

Text #7

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6560. Min Act: -0.0000

Data Index: 254128 (The Pile)

Max Activating Token Index: 366

Text #8

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1527205 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6727. Min Act: -0.0000

Data Index: 1554419 (The Pile)

Max Activating Token Index: 163

Text #10

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6829. Min Act: -0.0000

Data Index: 771885 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6138. Min Act: -0.0000

Data Index: 415516 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.7045. Min Act: -0.0000

Data Index: 406207 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1551674 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1949573 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6213. Min Act: -0.0000

Data Index: 1074575 (The Pile)

Max Activating Token Index: 109

Text #16

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1591509 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6780. Min Act: -0.0000

Data Index: 1340263 (The Pile)

Max Activating Token Index: 197

Text #18

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.6176. Min Act: -0.0000

Data Index: 1056708 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.8448. Min Range: -0.8448

Max Act: 0.5923. Min Act: -0.0000

Data Index: 782531 (The Pile)

Max Activating Token Index: 675