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

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

Neuron 3757 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: 0.6260. Min Range: -0.6260

Max Act: 0.6260. Min Act: -0.0000

Data Index: 727766 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1113343 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5939. Min Act: -0.0000

Data Index: 651778 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5018. Min Act: -0.0000

Data Index: 24361 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4947. Min Act: -0.0000

Data Index: 189817 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5465. Min Act: -0.0000

Data Index: 555764 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5250. Min Act: -0.0000

Data Index: 182052 (C4 (Web Text))

Max Activating Token Index: 680

Text #7

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5186. Min Act: -0.0000

Data Index: 576822 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5229. Min Act: -0.0000

Data Index: 1127975 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4813. Min Act: -0.0000

Data Index: 977822 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.5260. Min Act: -0.0000

Data Index: 316489 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4728. Min Act: -0.0000

Data Index: 190272 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4513. Min Act: -0.0000

Data Index: 432962 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4474. Min Act: -0.0000

Data Index: 240798 (C4 (Web Text))

Max Activating Token Index: 327

Text #14

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1237908 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4253. Min Act: -0.0000

Data Index: 217408 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4564. Min Act: -0.0000

Data Index: 146551 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4643. Min Act: -0.0000

Data Index: 167272 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4636. Min Act: -0.0000

Data Index: 1169177 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.6260. Min Range: -0.6260

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1009005 (C4 (Web Text))

Max Activating Token Index: 940