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

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

Neuron 2597 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.5005. Min Act: -0.0001

Data Index: 1177701 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.3409. Min Act: -0.0000

Data Index: 258368 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.3463. Min Act: -0.0000

Data Index: 1121847 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.2802. Min Act: -0.0001

Data Index: 305485 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.5005. Min Range: -1.5005

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1034414 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8993. Min Act: -0.0001

Data Index: 517319 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8883. Min Act: -0.0001

Data Index: 1433905 (Python Code)

Max Activating Token Index: 977

Text #7

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.9397. Min Act: -0.0001

Data Index: 1308950 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.9071. Min Act: -0.0001

Data Index: 637574 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8607. Min Act: -0.0001

Data Index: 1261102 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8637. Min Act: -0.0000

Data Index: 3791 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8953. Min Act: -0.0000

Data Index: 847535 (C4 (Web Text))

Max Activating Token Index: 152

Text #12

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8227. Min Act: -0.0000

Data Index: 417790 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8532. Min Act: -0.0000

Data Index: 1175397 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1344553 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.8392. Min Act: -0.0001

Data Index: 1172140 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.7831. Min Act: -0.0000

Data Index: 505573 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.7873. Min Act: -0.0001

Data Index: 998286 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.7477. Min Act: -0.0001

Data Index: 1563615 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 1.5005. Min Range: -1.5005

Max Act: 0.7468. Min Act: -0.0001

Data Index: 1543649 (Python Code)

Max Activating Token Index: 934