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

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

Neuron 3673 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: 1.3653. Min Range: -1.3653

Max Act: 1.3653. Min Act: -0.0001

Data Index: 1204236 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.1638. Min Act: -0.0001

Data Index: 146220 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.2093. Min Act: -0.0001

Data Index: 1006789 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.2173. Min Act: -0.0001

Data Index: 1111439 (C4 (Web Text))

Max Activating Token Index: 749

Text #4

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.1491. Min Act: -0.0001

Data Index: 822741 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0179. Min Act: -0.0001

Data Index: 500184 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0729. Min Act: -0.0001

Data Index: 895925 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0391. Min Act: -0.0001

Data Index: 283311 (C4 (Web Text))

Max Activating Token Index: 288

Text #8

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0994. Min Act: -0.0001

Data Index: 1062500 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0267. Min Act: -0.0001

Data Index: 1118936 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0772. Min Act: -0.0001

Data Index: 1248005 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9371. Min Act: -0.0001

Data Index: 1264635 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9757. Min Act: -0.0001

Data Index: 1030248 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0243. Min Act: -0.0001

Data Index: 416516 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9966. Min Act: -0.0001

Data Index: 196106 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 1.3653. Min Range: -1.3653

Max Act: 1.0240. Min Act: -0.0001

Data Index: 322257 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9482. Min Act: -0.0001

Data Index: 532501 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9496. Min Act: -0.0001

Data Index: 732184 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9587. Min Act: -0.0001

Data Index: 1036053 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 1.3653. Min Range: -1.3653

Max Act: 0.9588. Min Act: -0.0001

Data Index: 861694 (C4 (Web Text))

Max Activating Token Index: 36