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

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

Neuron 1973 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: 0.0985. Min Range: -0.0985

Max Act: 0.0864. Min Act: -0.0000

Data Index: 1304197 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0985. Min Act: -0.0000

Data Index: 263608 (C4 (Web Text))

Max Activating Token Index: 657

Text #2

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0890. Min Act: -0.0000

Data Index: 611483 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0910. Min Act: -0.0000

Data Index: 486668 (C4 (Web Text))

Max Activating Token Index: 311

Text #4

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1036685 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0814. Min Act: -0.0000

Data Index: 750227 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0814. Min Act: -0.0000

Data Index: 248630 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0731. Min Act: -0.0000

Data Index: 565030 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1153900 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0791. Min Act: -0.0000

Data Index: 373840 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1099938 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0700. Min Act: -0.0000

Data Index: 243416 (C4 (Web Text))

Max Activating Token Index: 102

Text #12

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0746. Min Act: -0.0000

Data Index: 197509 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1093855 (C4 (Web Text))

Max Activating Token Index: 203

Text #14

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1207940 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0658. Min Act: -0.0000

Data Index: 80494 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1162014 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0731. Min Act: -0.0000

Data Index: 403856 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0702. Min Act: -0.0000

Data Index: 726243 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.0985. Min Range: -0.0985

Max Act: 0.0655. Min Act: -0.0000

Data Index: 1012354 (C4 (Web Text))

Max Activating Token Index: 1016