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

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

Neuron 2798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.3647. Min Act: -0.0000

Data Index: 661882 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.2383. Min Act: -0.0000

Data Index: 497279 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1884. Min Act: -0.0000

Data Index: 986677 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1605. Min Act: -0.0000

Data Index: 27233 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1271. Min Act: -0.0000

Data Index: 618671 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.0929. Min Act: -0.0000

Data Index: 133910 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1259. Min Act: -0.0000

Data Index: 435251 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.0746. Min Act: -0.0000

Data Index: 957174 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.1182. Min Act: -0.0000

Data Index: 771691 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.0845. Min Act: -0.0000

Data Index: 897497 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.0309. Min Act: -0.0000

Data Index: 1196964 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 1.3647. Min Range: -1.3647

Max Act: 1.0384. Min Act: -0.0000

Data Index: 639126 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9685. Min Act: -0.0000

Data Index: 121174 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9812. Min Act: -0.0000

Data Index: 653265 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9822. Min Act: -0.0000

Data Index: 875578 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1598814 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9785. Min Act: -0.0000

Data Index: 895895 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9713. Min Act: -0.0000

Data Index: 121178 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9364. Min Act: -0.0000

Data Index: 523790 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.3647. Min Range: -1.3647

Max Act: 0.9259. Min Act: -0.0000

Data Index: 367384 (C4 (Web Text))

Max Activating Token Index: 990