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

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

Neuron 2074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4090. Min Range: -2.4090

Max Act: 2.4090. Min Act: -0.0000

Data Index: 1129462 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 2.4090. Min Range: -2.4090

Max Act: 2.2158. Min Act: -0.0000

Data Index: 1144480 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 2.4090. Min Range: -2.4090

Max Act: 2.1158. Min Act: -0.0000

Data Index: 1140696 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.9922. Min Act: -0.0000

Data Index: 1002385 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.7909. Min Act: -0.0000

Data Index: 561418 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 2.4090. Min Range: -2.4090

Max Act: 2.0249. Min Act: -0.0000

Data Index: 568116 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8947. Min Act: -0.0000

Data Index: 1051685 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8769. Min Act: -0.0000

Data Index: 866977 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.9465. Min Act: -0.0000

Data Index: 420424 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8232. Min Act: -0.0000

Data Index: 451647 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.9670. Min Act: -0.0000

Data Index: 1304261 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8209. Min Act: -0.0000

Data Index: 649301 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8696. Min Act: -0.0000

Data Index: 1350502 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1348356 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8756. Min Act: -0.0000

Data Index: 227241 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.6582. Min Act: -0.0000

Data Index: 301116 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8475. Min Act: -0.0000

Data Index: 966476 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.7192. Min Act: -0.0000

Data Index: 152866 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.8109. Min Act: -0.0000

Data Index: 260278 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 2.4090. Min Range: -2.4090

Max Act: 1.7216. Min Act: -0.0000

Data Index: 413472 (C4 (Web Text))

Max Activating Token Index: 682