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

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

Neuron 376 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.6557. Min Act: -0.0000

Data Index: 966448 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5687. Min Act: -0.0000

Data Index: 347629 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.5483. Min Act: -0.0000

Data Index: 237909 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1337590 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.4102. Min Act: -0.0000

Data Index: 910310 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1422470 (Python Code)

Max Activating Token Index: 363

Text #6

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2821. Min Act: -0.0000

Data Index: 811269 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2914. Min Act: -0.0000

Data Index: 31909 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1248. Min Act: -0.0000

Data Index: 848788 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.2220. Min Act: -0.0000

Data Index: 250596 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1534. Min Act: -0.0000

Data Index: 478496 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1171. Min Act: -0.0000

Data Index: 135418 (C4 (Web Text))

Max Activating Token Index: 535

Text #12

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1599. Min Act: -0.0000

Data Index: 988441 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1147387 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0959. Min Act: -0.0000

Data Index: 549938 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1096. Min Act: -0.0000

Data Index: 403611 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.1931. Min Act: -0.0000

Data Index: 1266254 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0941. Min Act: -0.0000

Data Index: 287884 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0018. Min Act: -0.0000

Data Index: 527003 (C4 (Web Text))

Max Activating Token Index: 64

Text #19

Max Range: 1.6557. Min Range: -1.6557

Max Act: 1.0654. Min Act: -0.0000

Data Index: 905388 (C4 (Web Text))

Max Activating Token Index: 449