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

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

Neuron 3823 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.9351. Min Act: -0.0001

Data Index: 338404 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.5653. Min Act: -0.0001

Data Index: 1576335 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.5095. Min Act: -0.0001

Data Index: 1172134 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.4473. Min Act: -0.0001

Data Index: 493918 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.5016. Min Act: -0.0001

Data Index: 597967 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.4610. Min Act: -0.0001

Data Index: 1435507 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.4516. Min Act: -0.0001

Data Index: 761268 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3952. Min Act: -0.0001

Data Index: 63312 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.4399. Min Act: -0.0001

Data Index: 409954 (C4 (Web Text))

Max Activating Token Index: 5

Text #9

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.4163. Min Act: -0.0001

Data Index: 1095156 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3381. Min Act: -0.0001

Data Index: 417170 (C4 (Web Text))

Max Activating Token Index: 587

Text #11

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3739. Min Act: -0.0001

Data Index: 1076532 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3591. Min Act: -0.0001

Data Index: 709161 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3937. Min Act: -0.0001

Data Index: 165979 (C4 (Web Text))

Max Activating Token Index: 64

Text #14

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.4465. Min Act: -0.0001

Data Index: 1476131 (Python Code)

Max Activating Token Index: 115

Text #15

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3826. Min Act: -0.0001

Data Index: 1484627 (Python Code)

Max Activating Token Index: 463

Text #16

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3572. Min Act: -0.0001

Data Index: 1021226 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3792. Min Act: -0.0001

Data Index: 1443716 (Python Code)

Max Activating Token Index: 147

Text #18

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3815. Min Act: -0.0001

Data Index: 1498086 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 1.9351. Min Range: -1.9351

Max Act: 1.3282. Min Act: -0.0001

Data Index: 1578989 (Python Code)

Max Activating Token Index: 287