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

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

Neuron 1478 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1331650 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0897. Min Act: -0.0002

Data Index: 177408 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0886. Min Act: -0.0002

Data Index: 642175 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0847. Min Act: -0.0002

Data Index: 897986 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0794. Min Act: -0.0002

Data Index: 848229 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1296529 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1284652 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0777. Min Act: -0.0002

Data Index: 495957 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0772. Min Act: -0.0002

Data Index: 771836 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0795. Min Act: -0.0003

Data Index: 236984 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0799. Min Act: -0.0002

Data Index: 166633 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0802. Min Act: -0.0002

Data Index: 645800 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1026668 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0761. Min Act: -0.0002

Data Index: 888916 (C4 (Web Text))

Max Activating Token Index: 833

Text #14

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0760. Min Act: -0.0002

Data Index: 917971 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0781. Min Act: -0.0002

Data Index: 1136993 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1275950 (C4 (Web Text))

Max Activating Token Index: 548

Text #17

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0749. Min Act: -0.0002

Data Index: 345254 (C4 (Web Text))

Max Activating Token Index: 850

Text #18

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0750. Min Act: -0.0002

Data Index: 352371 (C4 (Web Text))

Max Activating Token Index: 5

Text #19

Max Range: 0.0929. Min Range: -0.0929

Max Act: 0.0667. Min Act: -0.0002

Data Index: 690871 (C4 (Web Text))

Max Activating Token Index: 186