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

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

Neuron 2825 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.6415. Min Act: -0.0000

Data Index: 693671 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.6092. Min Act: -0.0000

Data Index: 1554049 (Python Code)

Max Activating Token Index: 572

Text #2

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.4726. Min Act: -0.0000

Data Index: 754452 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3654. Min Act: -0.0000

Data Index: 1411941 (Python Code)

Max Activating Token Index: 175

Text #4

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.4044. Min Act: -0.0000

Data Index: 986657 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3784. Min Act: -0.0000

Data Index: 1482661 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3796. Min Act: -0.0000

Data Index: 1585372 (Python Code)

Max Activating Token Index: 645

Text #7

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3670. Min Act: -0.0000

Data Index: 1122774 (C4 (Web Text))

Max Activating Token Index: 683

Text #8

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3610. Min Act: -0.0000

Data Index: 1590631 (Python Code)

Max Activating Token Index: 178

Text #9

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3630. Min Act: -0.0000

Data Index: 285309 (C4 (Web Text))

Max Activating Token Index: 744

Text #10

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3358. Min Act: -0.0000

Data Index: 1016747 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3257. Min Act: -0.0000

Data Index: 953873 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1532826 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3944. Min Act: -0.0000

Data Index: 42081 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1418437 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2997. Min Act: -0.0000

Data Index: 1484667 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1489395 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2038. Min Act: -0.0000

Data Index: 739878 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2729. Min Act: -0.0000

Data Index: 599665 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 1.6415. Min Range: -1.6415

Max Act: 1.2562. Min Act: -0.0000

Data Index: 54992 (C4 (Web Text))

Max Activating Token Index: 785