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

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

Neuron 3384 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.8661. Min Act: -0.0000

Data Index: 917574 (C4 (Web Text))

Max Activating Token Index: 447

Text #1

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1338943 (C4 (Web Text))

Max Activating Token Index: 352

Text #2

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.3691. Min Act: -0.0000

Data Index: 1260521 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.2561. Min Act: -0.0000

Data Index: 687431 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.2303. Min Act: -0.0000

Data Index: 1139019 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.1150. Min Act: -0.0000

Data Index: 543256 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.1475. Min Act: -0.0000

Data Index: 745587 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.1404. Min Act: -0.0000

Data Index: 545694 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.1163. Min Act: -0.0000

Data Index: 670603 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0008. Min Act: -0.0000

Data Index: 828747 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.1263. Min Act: -0.0000

Data Index: 733524 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0436. Min Act: -0.0000

Data Index: 196285 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0399. Min Act: -0.0000

Data Index: 865893 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0278. Min Act: -0.0000

Data Index: 357253 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0141. Min Act: -0.0000

Data Index: 288940 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0100. Min Act: -0.0000

Data Index: 999659 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 1.8661. Min Range: -1.8661

Max Act: 0.9888. Min Act: -0.0000

Data Index: 1055250 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0329. Min Act: -0.0000

Data Index: 673440 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 1.8661. Min Range: -1.8661

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1024508 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 1.8661. Min Range: -1.8661

Max Act: 0.9899. Min Act: -0.0000

Data Index: 61916 (C4 (Web Text))

Max Activating Token Index: 455