Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 853 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.7460. Min Act: -0.0001

Data Index: 708862 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.7660. Min Act: -0.0001

Data Index: 72706 (C4 (Web Text))

Max Activating Token Index: 75

Text #2

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.7041. Min Act: -0.0001

Data Index: 667228 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.6688. Min Act: -0.0001

Data Index: 101405 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5725. Min Act: -0.0001

Data Index: 1079945 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5024. Min Act: -0.0001

Data Index: 327840 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5468. Min Act: -0.0001

Data Index: 816166 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5051. Min Act: -0.0001

Data Index: 1116784 (C4 (Web Text))

Max Activating Token Index: 314

Text #8

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.5517. Min Act: -0.0001

Data Index: 274146 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3454. Min Act: -0.0001

Data Index: 207478 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4380. Min Act: -0.0001

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.4096. Min Act: -0.0001

Data Index: 1321583 (C4 (Web Text))

Max Activating Token Index: 91

Text #12

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3387. Min Act: -0.0001

Data Index: 1158950 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3379. Min Act: -0.0001

Data Index: 851580 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3279. Min Act: -0.0001

Data Index: 28094 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3627. Min Act: -0.0001

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.3032. Min Act: -0.0001

Data Index: 556001 (C4 (Web Text))

Max Activating Token Index: 433

Text #17

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.2548. Min Act: -0.0001

Data Index: 931462 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.2855. Min Act: -0.0001

Data Index: 768351 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 1.7660. Min Range: -1.7660

Max Act: 1.2819. Min Act: -0.0001

Data Index: 746636 (C4 (Web Text))

Max Activating Token Index: 143