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

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

Neuron 4437 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7518. Min Range: -5.7518

Max Act: 5.7518. Min Act: -0.0000

Data Index: 622894 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 5.7518. Min Range: -5.7518

Max Act: 5.2742. Min Act: -0.0000

Data Index: 544348 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 5.7518. Min Range: -5.7518

Max Act: 5.3568. Min Act: -0.0000

Data Index: 37625 (C4 (Web Text))

Max Activating Token Index: 563

Text #3

Max Range: 5.7518. Min Range: -5.7518

Max Act: 5.1949. Min Act: -0.0000

Data Index: 10236 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.8821. Min Act: -0.0000

Data Index: 280484 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 5.7518. Min Range: -5.7518

Max Act: 5.2651. Min Act: -0.0000

Data Index: 248293 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.8886. Min Act: -0.0000

Data Index: 953496 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 5.7518. Min Range: -5.7518

Max Act: 5.0059. Min Act: -0.0000

Data Index: 1043986 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.2094. Min Act: -0.0000

Data Index: 352844 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.4385. Min Act: -0.0000

Data Index: 15484 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.4911. Min Act: -0.0000

Data Index: 1271874 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.1586. Min Act: -0.0000

Data Index: 798949 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.4166. Min Act: -0.0000

Data Index: 1254155 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.3071. Min Act: -0.0000

Data Index: 954334 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.0156. Min Act: -0.0000

Data Index: 922921 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 5.7518. Min Range: -5.7518

Max Act: 3.9115. Min Act: -0.0000

Data Index: 39466 (C4 (Web Text))

Max Activating Token Index: 920

Text #16

Max Range: 5.7518. Min Range: -5.7518

Max Act: 3.8828. Min Act: -0.0000

Data Index: 420361 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 5.7518. Min Range: -5.7518

Max Act: 4.1844. Min Act: -0.0001

Data Index: 272527 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 5.7518. Min Range: -5.7518

Max Act: 3.7756. Min Act: -0.0000

Data Index: 150838 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 5.7518. Min Range: -5.7518

Max Act: 3.8804. Min Act: -0.0000

Data Index: 1209428 (C4 (Web Text))

Max Activating Token Index: 62