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

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

Neuron 4628 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.4025. Min Act: -0.0000

Data Index: 1426628 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.1514. Min Act: -0.0000

Data Index: 1619933 (Python Code)

Max Activating Token Index: 637

Text #2

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.2590. Min Act: -0.0000

Data Index: 1083477 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.0836. Min Act: -0.0000

Data Index: 1613343 (Python Code)

Max Activating Token Index: 1018

Text #4

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.0309. Min Act: -0.0000

Data Index: 1077169 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 2.4025. Min Range: -2.4025

Max Act: 2.1233. Min Act: -0.0000

Data Index: 824864 (C4 (Web Text))

Max Activating Token Index: 593

Text #6

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.8822. Min Act: -0.0000

Data Index: 644156 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.9707. Min Act: -0.0000

Data Index: 417868 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.8480. Min Act: 0.0000

Data Index: 1465101 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.8478. Min Act: -0.0000

Data Index: 114182 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.8115. Min Act: -0.0000

Data Index: 1580939 (Python Code)

Max Activating Token Index: 465

Text #11

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7085. Min Act: -0.0000

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7559. Min Act: -0.0000

Data Index: 1651759 (Python Code)

Max Activating Token Index: 19

Text #13

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7519. Min Act: -0.0000

Data Index: 1437865 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7974. Min Act: 0.0001

Data Index: 1485120 (Python Code)

Max Activating Token Index: 66

Text #15

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7373. Min Act: -0.0000

Data Index: 1591361 (Python Code)

Max Activating Token Index: 356

Text #16

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7315. Min Act: -0.0000

Data Index: 859454 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7395. Min Act: -0.0000

Data Index: 1426977 (Python Code)

Max Activating Token Index: 673

Text #18

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.7355. Min Act: -0.0000

Data Index: 1625841 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 2.4025. Min Range: -2.4025

Max Act: 1.6037. Min Act: -0.0000

Data Index: 549547 (C4 (Web Text))

Max Activating Token Index: 1013