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

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

Neuron 1175 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: 1.8815. Min Range: -1.8815

Max Act: 1.8815. Min Act: -0.0000

Data Index: 1596946 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.6251. Min Act: -0.0000

Data Index: 538199 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.4655. Min Act: -0.0000

Data Index: 235032 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3800. Min Act: -0.0000

Data Index: 345243 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3180. Min Act: -0.0000

Data Index: 1615222 (Python Code)

Max Activating Token Index: 1002

Text #5

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1559062 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.5117. Min Act: -0.0000

Data Index: 1487263 (Python Code)

Max Activating Token Index: 225

Text #7

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1461683 (Python Code)

Max Activating Token Index: 498

Text #8

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.4579. Min Act: -0.0000

Data Index: 675909 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3493. Min Act: -0.0000

Data Index: 562858 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3501. Min Act: -0.0000

Data Index: 1112387 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.2414. Min Act: -0.0000

Data Index: 544856 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.2332. Min Act: -0.0000

Data Index: 1216759 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.2947. Min Act: -0.0000

Data Index: 422507 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3099. Min Act: -0.0000

Data Index: 519205 (C4 (Web Text))

Max Activating Token Index: 447

Text #15

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.2155. Min Act: -0.0000

Data Index: 1435651 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.3304. Min Act: -0.0000

Data Index: 59164 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.2783. Min Act: -0.0000

Data Index: 174602 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1440359 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 1.8815. Min Range: -1.8815

Max Act: 1.1208. Min Act: -0.0000

Data Index: 1543231 (Python Code)

Max Activating Token Index: 202