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

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

Neuron 2640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.4411. Min Act: -0.0000

Data Index: 1422766 (Python Code)

Max Activating Token Index: 369

Text #1

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.3285. Min Act: -0.0000

Data Index: 112349 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.2527. Min Act: -0.0000

Data Index: 762308 (C4 (Web Text))

Max Activating Token Index: 683

Text #3

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1402767 (Python Code)

Max Activating Token Index: 86

Text #4

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1392052 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1340. Min Act: -0.0000

Data Index: 1019483 (C4 (Web Text))

Max Activating Token Index: 826

Text #6

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1231. Min Act: -0.0000

Data Index: 931613 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1195. Min Act: -0.0000

Data Index: 433288 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1235. Min Act: -0.0000

Data Index: 1482683 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1683. Min Act: -0.0000

Data Index: 584816 (C4 (Web Text))

Max Activating Token Index: 366

Text #10

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0986. Min Act: -0.0000

Data Index: 1318373 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0832. Min Act: -0.0000

Data Index: 316004 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.1102. Min Act: -0.0000

Data Index: 444708 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0371. Min Act: -0.0000

Data Index: 1490453 (Python Code)

Max Activating Token Index: 316

Text #14

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0090. Min Act: -0.0001

Data Index: 1582999 (Python Code)

Max Activating Token Index: 723

Text #15

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0045. Min Act: -0.0001

Data Index: 1393701 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0423. Min Act: -0.0000

Data Index: 1524658 (Python Code)

Max Activating Token Index: 72

Text #17

Max Range: 1.4411. Min Range: -1.4411

Max Act: 1.0786. Min Act: -0.0000

Data Index: 1656259 (Python Code)

Max Activating Token Index: 605

Text #18

Max Range: 1.4411. Min Range: -1.4411

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1327640 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 1.4411. Min Range: -1.4411

Max Act: 0.9656. Min Act: -0.0000

Data Index: 795598 (C4 (Web Text))

Max Activating Token Index: 36