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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1558 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0916. Min Act: -0.0001

Data Index: 282445 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0879. Min Act: -0.0001

Data Index: 258873 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1204700 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0758. Min Act: -0.0001

Data Index: 455545 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0770. Min Act: -0.0000

Data Index: 720261 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0770. Min Act: -0.0001

Data Index: 542950 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0731. Min Act: -0.0001

Data Index: 219593 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1066861 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1028303 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0722. Min Act: -0.0001

Data Index: 568224 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1210711 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0748. Min Act: -0.0001

Data Index: 1035264 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0766. Min Act: -0.0000

Data Index: 244026 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0731. Min Act: -0.0000

Data Index: 1207169 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0709. Min Act: -0.0000

Data Index: 845247 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1095333 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0721. Min Act: -0.0000

Data Index: 938291 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0723. Min Act: -0.0000

Data Index: 81157 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1016548 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.0916. Min Range: -0.0916

Max Act: 0.0679. Min Act: -0.0000

Data Index: 467314 (C4 (Web Text))

Max Activating Token Index: 549