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

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

Neuron 1691 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: 1.4378. Min Range: -1.4378

Max Act: 1.4378. Min Act: -0.0000

Data Index: 979300 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.3069. Min Act: -0.0000

Data Index: 252530 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1794. Min Act: -0.0000

Data Index: 394402 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1997. Min Act: -0.0000

Data Index: 837015 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1437. Min Act: -0.0000

Data Index: 566155 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.2072. Min Act: -0.0000

Data Index: 1162499 (C4 (Web Text))

Max Activating Token Index: 38

Text #6

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1687. Min Act: -0.0000

Data Index: 380400 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1913. Min Act: -0.0000

Data Index: 288298 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1569. Min Act: -0.0000

Data Index: 48655 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1962. Min Act: -0.0000

Data Index: 328983 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0756. Min Act: -0.0000

Data Index: 443631 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.1376. Min Act: -0.0000

Data Index: 1173114 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0466. Min Act: -0.0000

Data Index: 993997 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0362. Min Act: -0.0000

Data Index: 757218 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1135238 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0633. Min Act: -0.0000

Data Index: 964667 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0820. Min Act: -0.0000

Data Index: 437301 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0619. Min Act: -0.0000

Data Index: 529452 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 1.4378. Min Range: -1.4378

Max Act: 1.0245. Min Act: -0.0000

Data Index: 179569 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.4378. Min Range: -1.4378

Max Act: 0.9907. Min Act: -0.0000

Data Index: 1194481 (C4 (Web Text))

Max Activating Token Index: 337