Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 406 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0006

Data Index: 785459 (C4 (Web Text))

Max Activating Token Index: 165

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0321. Min Act: -0.0006

Data Index: 978688 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0324. Min Act: -0.0006

Data Index: 917477 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0321. Min Act: -0.0006

Data Index: 68075 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0311. Min Act: -0.0006

Data Index: 899589 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0315. Min Act: -0.0006

Data Index: 506777 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0309. Min Act: -0.0006

Data Index: 233919 (C4 (Web Text))

Max Activating Token Index: 630

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1056947 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0300. Min Act: -0.0006

Data Index: 883374 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0302. Min Act: -0.0006

Data Index: 333792 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0303. Min Act: -0.0006

Data Index: 1000168 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0295. Min Act: -0.0006

Data Index: 950910 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0288. Min Act: -0.0006

Data Index: 75657 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0299. Min Act: -0.0006

Data Index: 813269 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0302. Min Act: -0.0006

Data Index: 563395 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0291. Min Act: -0.0006

Data Index: 566984 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0311. Min Act: -0.0006

Data Index: 935901 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0006

Data Index: 1268803 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1229572 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0282. Min Act: -0.0006

Data Index: 935148 (C4 (Web Text))

Max Activating Token Index: 594