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

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

Neuron 5047 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: 0.8282. Min Range: -0.8282

Max Act: 0.7888. Min Act: -0.0002

Data Index: 1106166 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.8282. Min Act: -0.0002

Data Index: 543134 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7594. Min Act: -0.0002

Data Index: 793038 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7636. Min Act: -0.0002

Data Index: 1353017 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7817. Min Act: -0.0002

Data Index: 341348 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.8025. Min Act: -0.0002

Data Index: 1197133 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7685. Min Act: -0.0002

Data Index: 1175659 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6990. Min Act: -0.0002

Data Index: 335676 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7327. Min Act: -0.0002

Data Index: 717329 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7343. Min Act: -0.0002

Data Index: 21571 (C4 (Web Text))

Max Activating Token Index: 451

Text #10

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7483. Min Act: -0.0002

Data Index: 729048 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7242. Min Act: -0.0002

Data Index: 1356286 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6935. Min Act: -0.0002

Data Index: 127362 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.7068. Min Act: -0.0002

Data Index: 462514 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6772. Min Act: -0.0002

Data Index: 101512 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.5739. Min Act: -0.0002

Data Index: 633730 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6935. Min Act: -0.0002

Data Index: 1335078 (C4 (Web Text))

Max Activating Token Index: 558

Text #17

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6814. Min Act: -0.0002

Data Index: 957351 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6404. Min Act: -0.0002

Data Index: 964783 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.8282. Min Range: -0.8282

Max Act: 0.6828. Min Act: -0.0002

Data Index: 408306 (C4 (Web Text))

Max Activating Token Index: 165