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

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

Neuron 3974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.8983. Min Act: -0.0000

Data Index: 642870 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.8888. Min Act: -0.0000

Data Index: 997470 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.7639. Min Act: -0.0000

Data Index: 155236 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.7867. Min Act: -0.0000

Data Index: 242357 (C4 (Web Text))

Max Activating Token Index: 339

Text #4

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.7269. Min Act: -0.0000

Data Index: 73945 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.8277. Min Act: -0.0000

Data Index: 653473 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.7195. Min Act: -0.0000

Data Index: 275019 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1186024 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6635. Min Act: -0.0000

Data Index: 327809 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6903. Min Act: -0.0000

Data Index: 146258 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6191. Min Act: -0.0000

Data Index: 807761 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6445. Min Act: -0.0000

Data Index: 860129 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6193. Min Act: -0.0000

Data Index: 23940 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.5898. Min Act: -0.0000

Data Index: 284986 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6103. Min Act: -0.0000

Data Index: 817000 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1176306 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.5935. Min Act: -0.0000

Data Index: 626904 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.5879. Min Act: -0.0000

Data Index: 211781 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.5342. Min Act: -0.0000

Data Index: 909001 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.8983. Min Range: -0.8983

Max Act: 0.6255. Min Act: -0.0000

Data Index: 647009 (C4 (Web Text))

Max Activating Token Index: 947