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

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

Neuron 1988 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3681. Min Act: -0.0000

Data Index: 235404 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3717. Min Act: -0.0000

Data Index: 263241 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3523. Min Act: -0.0000

Data Index: 406136 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3498. Min Act: -0.0000

Data Index: 968994 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1562088 (Python Code)

Max Activating Token Index: 478

Text #5

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3205. Min Act: -0.0000

Data Index: 1561204 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3532. Min Act: -0.0000

Data Index: 1064687 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3274. Min Act: -0.0000

Data Index: 1487586 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3126. Min Act: -0.0000

Data Index: 268385 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3573. Min Act: -0.0000

Data Index: 743958 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3313. Min Act: -0.0000

Data Index: 428129 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3124. Min Act: -0.0000

Data Index: 776183 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3239. Min Act: -0.0000

Data Index: 574399 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1531783 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1119215 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3229. Min Act: -0.0000

Data Index: 1416333 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3019. Min Act: -0.0000

Data Index: 1326999 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3071. Min Act: -0.0000

Data Index: 1231682 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.2798. Min Act: -0.0000

Data Index: 6446 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.3717. Min Range: -0.3717

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1117168 (C4 (Web Text))

Max Activating Token Index: 806