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

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

Neuron 5396 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.2324. Min Act: -0.0000

Data Index: 249910 (C4 (Web Text))

Max Activating Token Index: 331

Text #1

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.2121. Min Act: -0.0000

Data Index: 1044182 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0947. Min Act: -0.0000

Data Index: 699853 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0411. Min Act: -0.0000

Data Index: 559082 (C4 (Web Text))

Max Activating Token Index: 283

Text #4

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0463. Min Act: -0.0000

Data Index: 979760 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0818. Min Act: -0.0000

Data Index: 651478 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1221378 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1551864 (Python Code)

Max Activating Token Index: 291

Text #8

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9855. Min Act: -0.0000

Data Index: 206799 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9938. Min Act: -0.0000

Data Index: 123103 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9425. Min Act: -0.0000

Data Index: 801552 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9137. Min Act: -0.0000

Data Index: 493496 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1035245 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1096818 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8789. Min Act: -0.0000

Data Index: 794421 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8789. Min Act: -0.0000

Data Index: 125578 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1473851 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9003. Min Act: -0.0000

Data Index: 148385 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8987. Min Act: 0.0000

Data Index: 1358081 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1428563 (Python Code)

Max Activating Token Index: 663