Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3292 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.6372. Min Range: -5.6372

Max Act: 5.4324. Min Act: -0.0001

Data Index: 970320 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 5.6372. Min Range: -5.6372

Max Act: 5.6372. Min Act: -0.0001

Data Index: 923372 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 5.6372. Min Range: -5.6372

Max Act: 4.2044. Min Act: -0.0000

Data Index: 137945 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.8907. Min Act: -0.0001

Data Index: 333785 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.9962. Min Act: -0.0001

Data Index: 565797 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.8957. Min Act: -0.0001

Data Index: 948664 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.5317. Min Act: -0.0001

Data Index: 1178534 (C4 (Web Text))

Max Activating Token Index: 385

Text #7

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.1282. Min Act: -0.0000

Data Index: 1078858 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.5373. Min Act: -0.0001

Data Index: 1318200 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.5250. Min Act: -0.0001

Data Index: 582008 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.4830. Min Act: -0.0001

Data Index: 406540 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.0201. Min Act: -0.0000

Data Index: 568956 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.3832. Min Act: -0.0000

Data Index: 1178092 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.6372. Min Range: -5.6372

Max Act: 2.9820. Min Act: -0.0000

Data Index: 1303801 (C4 (Web Text))

Max Activating Token Index: 778

Text #14

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.2024. Min Act: -0.0001

Data Index: 825470 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.7891. Min Act: -0.0001

Data Index: 145244 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.1468. Min Act: -0.0001

Data Index: 1071274 (C4 (Web Text))

Max Activating Token Index: 10

Text #17

Max Range: 5.6372. Min Range: -5.6372

Max Act: 2.8376. Min Act: -0.0001

Data Index: 675643 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 5.6372. Min Range: -5.6372

Max Act: 2.9756. Min Act: -0.0000

Data Index: 1051883 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 5.6372. Min Range: -5.6372

Max Act: 3.0518. Min Act: -0.0000

Data Index: 89411 (C4 (Web Text))

Max Activating Token Index: 114