Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 849 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.6479. Min Act: -0.0001

Data Index: 967060 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.5096. Min Act: -0.0001

Data Index: 57059 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.4419. Min Act: -0.0001

Data Index: 222552 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.4043. Min Act: -0.0001

Data Index: 365220 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3504. Min Act: -0.0001

Data Index: 222553 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3780. Min Act: -0.0001

Data Index: 160076 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3792. Min Act: -0.0001

Data Index: 543771 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3780. Min Act: -0.0001

Data Index: 1045357 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3763. Min Act: -0.0001

Data Index: 820702 (C4 (Web Text))

Max Activating Token Index: 335

Text #9

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3695. Min Act: -0.0001

Data Index: 717918 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3303. Min Act: -0.0001

Data Index: 710989 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3185. Min Act: -0.0001

Data Index: 58713 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3604. Min Act: -0.0001

Data Index: 1347987 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3084. Min Act: -0.0001

Data Index: 1339538 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3048. Min Act: -0.0001

Data Index: 1180157 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1475529 (Python Code)

Max Activating Token Index: 85

Text #16

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.2554. Min Act: -0.0001

Data Index: 393354 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.3309. Min Act: -0.0001

Data Index: 237609 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.2367. Min Act: -0.0001

Data Index: 963828 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 1.6479. Min Range: -1.6479

Max Act: 1.2694. Min Act: -0.0001

Data Index: 1228702 (C4 (Web Text))

Max Activating Token Index: 140