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

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

Neuron 708 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0875. Min Act: -0.0000

Data Index: 387636 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.1563. Min Act: -0.0000

Data Index: 2526 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0232. Min Act: -0.0000

Data Index: 178808 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0388. Min Act: -0.0000

Data Index: 478616 (C4 (Web Text))

Max Activating Token Index: 638

Text #4

Max Range: 1.1563. Min Range: -1.1563

Max Act: 1.0265. Min Act: -0.0000

Data Index: 886556 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1043423 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8847. Min Act: -0.0000

Data Index: 497605 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1309266 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8654. Min Act: -0.0000

Data Index: 372714 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8427. Min Act: -0.0000

Data Index: 1272098 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8536. Min Act: -0.0000

Data Index: 323593 (C4 (Web Text))

Max Activating Token Index: 250

Text #11

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.8675. Min Act: -0.0000

Data Index: 94910 (C4 (Web Text))

Max Activating Token Index: 617

Text #12

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1009172 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7783. Min Act: -0.0000

Data Index: 1089433 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1326641 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1050416 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7573. Min Act: -0.0000

Data Index: 31688 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7559. Min Act: -0.0000

Data Index: 1315543 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7777. Min Act: -0.0000

Data Index: 657744 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 1.1563. Min Range: -1.1563

Max Act: 0.7399. Min Act: -0.0000

Data Index: 891889 (C4 (Web Text))

Max Activating Token Index: 132