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

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

Neuron 4003 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.8093. Min Act: -0.0000

Data Index: 668354 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.6894. Min Act: -0.0000

Data Index: 243409 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.6944. Min Act: -0.0000

Data Index: 1363624 (Python Code)

Max Activating Token Index: 16

Text #3

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.6683. Min Act: -0.0000

Data Index: 924225 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.7703. Min Act: -0.0000

Data Index: 397605 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.6408. Min Act: -0.0000

Data Index: 1330367 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.4596. Min Act: -0.0000

Data Index: 113260 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.4438. Min Act: -0.0000

Data Index: 1254659 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.4068. Min Act: -0.0000

Data Index: 1458715 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.3625. Min Act: -0.0000

Data Index: 877982 (C4 (Web Text))

Max Activating Token Index: 676

Text #10

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.4738. Min Act: -0.0000

Data Index: 25938 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.3059. Min Act: -0.0000

Data Index: 677446 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.2328. Min Act: -0.0000

Data Index: 630028 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.3111. Min Act: -0.0000

Data Index: 646857 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.2956. Min Act: -0.0000

Data Index: 1062958 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.1860. Min Act: -0.0000

Data Index: 1275770 (C4 (Web Text))

Max Activating Token Index: 933

Text #16

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.2161. Min Act: -0.0000

Data Index: 306166 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.2007. Min Act: -0.0000

Data Index: 900797 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.2319. Min Act: -0.0000

Data Index: 516887 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 2.8093. Min Range: -2.8093

Max Act: 2.1553. Min Act: -0.0000

Data Index: 409080 (C4 (Web Text))

Max Activating Token Index: 931