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

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

Neuron 1644 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.8362. Min Act: -0.0000

Data Index: 172837 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.5949. Min Act: -0.0000

Data Index: 741093 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.6947. Min Act: -0.0000

Data Index: 423493 (C4 (Web Text))

Max Activating Token Index: 803

Text #3

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.2103. Min Act: -0.0000

Data Index: 917010 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.2747. Min Act: -0.0000

Data Index: 1121999 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.1311. Min Act: -0.0000

Data Index: 1418266 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.2367. Min Act: -0.0000

Data Index: 327817 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.9566. Min Act: -0.0000

Data Index: 974813 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.0245. Min Act: -0.0000

Data Index: 1426297 (Python Code)

Max Activating Token Index: 388

Text #9

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1571693 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.8753. Min Act: -0.0000

Data Index: 125732 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.9532. Min Act: -0.0000

Data Index: 184197 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.8384. Min Act: -0.0000

Data Index: 29440 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.1555. Min Act: -0.0000

Data Index: 278334 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.8926. Min Act: -0.0000

Data Index: 1136608 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.8858. Min Act: -0.0000

Data Index: 822668 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.7795. Min Act: -0.0000

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.8729. Min Act: -0.0000

Data Index: 1640625 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 2.8362. Min Range: -2.8362

Max Act: 1.8646. Min Act: -0.0000

Data Index: 12856 (C4 (Web Text))

Max Activating Token Index: 187

Text #19

Max Range: 2.8362. Min Range: -2.8362

Max Act: 2.0621. Min Act: -0.0000

Data Index: 720329 (C4 (Web Text))

Max Activating Token Index: 269