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

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

Neuron 260 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.5004. Min Act: -0.0000

Data Index: 568286 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3774. Min Act: -0.0000

Data Index: 205496 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3722. Min Act: -0.0000

Data Index: 698269 (C4 (Web Text))

Max Activating Token Index: 562

Text #3

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3796. Min Act: -0.0000

Data Index: 481121 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3666. Min Act: -0.0000

Data Index: 178107 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1275369 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3439. Min Act: -0.0000

Data Index: 983844 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3171. Min Act: -0.0000

Data Index: 396916 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3225. Min Act: -0.0000

Data Index: 1232707 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2979. Min Act: -0.0000

Data Index: 50608 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3006. Min Act: -0.0000

Data Index: 582044 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3010. Min Act: -0.0000

Data Index: 235706 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2870. Min Act: -0.0000

Data Index: 438822 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.3102. Min Act: -0.0000

Data Index: 1321940 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2912. Min Act: -0.0000

Data Index: 360367 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1054979 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2696. Min Act: -0.0000

Data Index: 1263039 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2780. Min Act: -0.0000

Data Index: 645559 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2622. Min Act: -0.0000

Data Index: 673415 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.5004. Min Range: -0.5004

Max Act: 0.2770. Min Act: -0.0000

Data Index: 724125 (C4 (Web Text))

Max Activating Token Index: 115