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

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

Neuron 3920 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: 0.3404. Min Range: -0.3404

Max Act: 0.3404. Min Act: 0.0001

Data Index: 508576 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2614. Min Act: -0.0000

Data Index: 998673 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1304130 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1221891 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2349. Min Act: -0.0000

Data Index: 509134 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2420. Min Act: -0.0000

Data Index: 211080 (C4 (Web Text))

Max Activating Token Index: 791

Text #6

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2440. Min Act: -0.0000

Data Index: 127827 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2280. Min Act: -0.0000

Data Index: 848120 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1206125 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2189. Min Act: -0.0000

Data Index: 239001 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2164. Min Act: -0.0000

Data Index: 53393 (C4 (Web Text))

Max Activating Token Index: 536

Text #11

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2074. Min Act: -0.0000

Data Index: 220624 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2069. Min Act: -0.0000

Data Index: 971105 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2055. Min Act: -0.0000

Data Index: 50116 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.1969. Min Act: -0.0000

Data Index: 615773 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2012. Min Act: -0.0000

Data Index: 517546 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2005. Min Act: -0.0000

Data Index: 748164 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.1989. Min Act: -0.0000

Data Index: 923548 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2059. Min Act: 0.0000

Data Index: 724714 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.3404. Min Range: -0.3404

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1352196 (C4 (Web Text))

Max Activating Token Index: 169