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

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

Neuron 4307 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0000

Data Index: 119857 (C4 (Web Text))

Max Activating Token Index: 815

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0522. Min Act: 0.0000

Data Index: 374425 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0484. Min Act: -0.0000

Data Index: 511116 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0461. Min Act: -0.0000

Data Index: 620108 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0405. Min Act: -0.0000

Data Index: 750235 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0399. Min Act: -0.0000

Data Index: 397616 (C4 (Web Text))

Max Activating Token Index: 740

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0425. Min Act: -0.0000

Data Index: 608695 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0404. Min Act: -0.0000

Data Index: 456133 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0422. Min Act: -0.0000

Data Index: 397626 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0406. Min Act: -0.0000

Data Index: 117181 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0403. Min Act: -0.0000

Data Index: 1419941 (Python Code)

Max Activating Token Index: 586

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0428. Min Act: -0.0000

Data Index: 230591 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0414. Min Act: -0.0000

Data Index: 1066957 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0379. Min Act: -0.0000

Data Index: 1277832 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0398. Min Act: -0.0000

Data Index: 151827 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0354. Min Act: -0.0000

Data Index: 1121202 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0337. Min Act: -0.0000

Data Index: 1128223 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0360. Min Act: -0.0000

Data Index: 435596 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0355. Min Act: -0.0000

Data Index: 440700 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0359. Min Act: -0.0000

Data Index: 691772 (C4 (Web Text))

Max Activating Token Index: 52