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

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

Neuron 5935 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.1632. Min Act: -0.0000

Data Index: 1277997 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 2.1632. Min Range: -2.1632

Max Act: 2.0680. Min Act: -0.0000

Data Index: 1260460 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.8958. Min Act: -0.0000

Data Index: 895720 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.7704. Min Act: -0.0000

Data Index: 371138 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.6522. Min Act: -0.0000

Data Index: 1057255 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.5798. Min Act: -0.0000

Data Index: 170583 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4553. Min Act: -0.0000

Data Index: 1086014 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4834. Min Act: -0.0000

Data Index: 1322500 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4778. Min Act: -0.0000

Data Index: 469973 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1271935 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.3652. Min Act: -0.0000

Data Index: 1127542 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4521. Min Act: -0.0000

Data Index: 1260707 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.3571. Min Act: -0.0000

Data Index: 453222 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4884. Min Act: -0.0000

Data Index: 616419 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4147. Min Act: -0.0000

Data Index: 492571 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4077. Min Act: -0.0000

Data Index: 1326150 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.4062. Min Act: -0.0000

Data Index: 160463 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.3852. Min Act: -0.0000

Data Index: 820861 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.3016. Min Act: -0.0000

Data Index: 479217 (C4 (Web Text))

Max Activating Token Index: 224

Text #19

Max Range: 2.1632. Min Range: -2.1632

Max Act: 1.3833. Min Act: -0.0000

Data Index: 541992 (C4 (Web Text))

Max Activating Token Index: 954