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

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

Neuron 2660 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: 2.1524. Min Range: -2.1524

Max Act: 2.1524. Min Act: -0.0000

Data Index: 967073 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 2.1524. Min Range: -2.1524

Max Act: 2.0571. Min Act: -0.0000

Data Index: 714074 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.9280. Min Act: -0.0000

Data Index: 390890 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.8751. Min Act: -0.0000

Data Index: 286512 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.8097. Min Act: -0.0000

Data Index: 389947 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.7807. Min Act: -0.0000

Data Index: 733323 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6929. Min Act: -0.0000

Data Index: 487385 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.5733. Min Act: -0.0000

Data Index: 183931 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6642. Min Act: -0.0000

Data Index: 1304973 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6244. Min Act: -0.0000

Data Index: 54277 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6219. Min Act: -0.0000

Data Index: 233855 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6210. Min Act: -0.0000

Data Index: 1056570 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.5030. Min Act: -0.0000

Data Index: 115918 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6841. Min Act: -0.0000

Data Index: 569980 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.5489. Min Act: -0.0000

Data Index: 308607 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.5617. Min Act: -0.0000

Data Index: 1242620 (C4 (Web Text))

Max Activating Token Index: 705

Text #16

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.6474. Min Act: -0.0000

Data Index: 483730 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.3886. Min Act: -0.0000

Data Index: 706538 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.3718. Min Act: -0.0000

Data Index: 1285936 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 2.1524. Min Range: -2.1524

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1234228 (C4 (Web Text))

Max Activating Token Index: 530