Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4605 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2567. Min Range: -1.2567

Max Act: 1.2567. Min Act: -0.0000

Data Index: 1533995 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 1.2567. Min Range: -1.2567

Max Act: 1.1787. Min Act: -0.0000

Data Index: 715501 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 1.2567. Min Range: -1.2567

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1049549 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 1.2567. Min Range: -1.2567

Max Act: 1.0547. Min Act: -0.0000

Data Index: 1007418 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9569. Min Act: -0.0000

Data Index: 1241299 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.2567. Min Range: -1.2567

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1157458 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.2567. Min Range: -1.2567

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1311707 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1415712 (Python Code)

Max Activating Token Index: 503

Text #8

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9892. Min Act: -0.0000

Data Index: 539344 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9073. Min Act: -0.0000

Data Index: 56489 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.8709. Min Act: -0.0000

Data Index: 976491 (C4 (Web Text))

Max Activating Token Index: 272

Text #11

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1087340 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1560124 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1368496 (Python Code)

Max Activating Token Index: 50

Text #14

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.8639. Min Act: -0.0000

Data Index: 146694 (C4 (Web Text))

Max Activating Token Index: 451

Text #15

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9213. Min Act: -0.0000

Data Index: 536451 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1426688 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.9482. Min Act: -0.0000

Data Index: 1232265 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1379803 (Python Code)

Max Activating Token Index: 270

Text #19

Max Range: 1.2567. Min Range: -1.2567

Max Act: 0.8193. Min Act: -0.0000

Data Index: 1248992 (C4 (Web Text))

Max Activating Token Index: 327