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

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

Neuron 1940 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.2369. Min Range: -4.2369

Max Act: 4.2369. Min Act: -0.0000

Data Index: 487109 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.7228. Min Act: -0.0000

Data Index: 347259 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.7063. Min Act: -0.0000

Data Index: 501256 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.6908. Min Act: -0.0000

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.6112. Min Act: -0.0000

Data Index: 1226482 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.2576. Min Act: -0.0000

Data Index: 884550 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.2156. Min Act: -0.0000

Data Index: 528395 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.0166. Min Act: -0.0000

Data Index: 223897 (C4 (Web Text))

Max Activating Token Index: 534

Text #8

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.1611. Min Act: -0.0000

Data Index: 1034376 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.1269. Min Act: -0.0000

Data Index: 266452 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.0855. Min Act: -0.0000

Data Index: 592129 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.2157. Min Act: -0.0000

Data Index: 302675 (C4 (Web Text))

Max Activating Token Index: 529

Text #12

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.7336. Min Act: -0.0000

Data Index: 971047 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.9517. Min Act: -0.0000

Data Index: 1038311 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 4.2369. Min Range: -4.2369

Max Act: 3.0521. Min Act: -0.0000

Data Index: 512758 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.7567. Min Act: -0.0000

Data Index: 580743 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.6818. Min Act: -0.0000

Data Index: 977249 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.7771. Min Act: -0.0000

Data Index: 1107898 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.7890. Min Act: -0.0000

Data Index: 969073 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 4.2369. Min Range: -4.2369

Max Act: 2.6491. Min Act: -0.0000

Data Index: 666002 (C4 (Web Text))

Max Activating Token Index: 830