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

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

Neuron 4507 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: 0.5404. Min Range: -0.5404

Max Act: 0.5404. Min Act: -0.0000

Data Index: 632991 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.5014. Min Act: -0.0000

Data Index: 994891 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4552. Min Act: -0.0000

Data Index: 314624 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1004120 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.4174. Min Act: -0.0000

Data Index: 201639 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3986. Min Act: -0.0000

Data Index: 1245387 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3842. Min Act: -0.0000

Data Index: 672129 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3590. Min Act: -0.0000

Data Index: 341530 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.2761. Min Act: -0.0000

Data Index: 758796 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1033097 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3409. Min Act: -0.0000

Data Index: 674062 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3655. Min Act: -0.0000

Data Index: 623042 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3513. Min Act: -0.0000

Data Index: 1123399 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3518. Min Act: -0.0000

Data Index: 279654 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3471. Min Act: -0.0000

Data Index: 746585 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3720. Min Act: -0.0000

Data Index: 732651 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3234. Min Act: -0.0000

Data Index: 394694 (C4 (Web Text))

Max Activating Token Index: 672

Text #17

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3448. Min Act: -0.0000

Data Index: 127309 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3396. Min Act: -0.0000

Data Index: 941872 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 0.5404. Min Range: -0.5404

Max Act: 0.3501. Min Act: -0.0000

Data Index: 424968 (C4 (Web Text))

Max Activating Token Index: 649