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

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

Neuron 4571 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: 0.4250. Min Range: -0.4250

Max Act: 0.4208. Min Act: -0.0000

Data Index: 71572 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.4250. Min Act: -0.0000

Data Index: 251528 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3888. Min Act: -0.0000

Data Index: 503050 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3615. Min Act: -0.0000

Data Index: 285671 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1263541 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1528599 (Python Code)

Max Activating Token Index: 820

Text #6

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3397. Min Act: -0.0000

Data Index: 449237 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3699. Min Act: -0.0000

Data Index: 15327 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3316. Min Act: -0.0000

Data Index: 1564895 (Python Code)

Max Activating Token Index: 58

Text #9

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3318. Min Act: -0.0000

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3122. Min Act: -0.0000

Data Index: 122388 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3278. Min Act: -0.0000

Data Index: 567071 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3154. Min Act: -0.0000

Data Index: 51320 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2856. Min Act: -0.0000

Data Index: 761286 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3126. Min Act: -0.0000

Data Index: 820455 (C4 (Web Text))

Max Activating Token Index: 323

Text #15

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3065. Min Act: -0.0000

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3166. Min Act: -0.0000

Data Index: 468787 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1311934 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1090458 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 0.4250. Min Range: -0.4250

Max Act: 0.3065. Min Act: -0.0000

Data Index: 956277 (C4 (Web Text))

Max Activating Token Index: 545