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

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

Neuron 3834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.9072. Min Act: -0.0000

Data Index: 1024399 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8629. Min Act: -0.0000

Data Index: 278216 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1309390 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8155. Min Act: -0.0000

Data Index: 870531 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1187430 (C4 (Web Text))

Max Activating Token Index: 432

Text #5

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7764. Min Act: -0.0000

Data Index: 85075 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7503. Min Act: -0.0000

Data Index: 922386 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7857. Min Act: -0.0000

Data Index: 203605 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.7183. Min Act: -0.0000

Data Index: 77344 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6700. Min Act: -0.0000

Data Index: 531175 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6844. Min Act: -0.0000

Data Index: 758586 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6232. Min Act: -0.0000

Data Index: 592241 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6717. Min Act: -0.0000

Data Index: 543448 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1081187 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6293. Min Act: -0.0000

Data Index: 685849 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6569. Min Act: -0.0000

Data Index: 476617 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6398. Min Act: -0.0000

Data Index: 671753 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.5944. Min Act: -0.0000

Data Index: 627949 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6345. Min Act: -0.0000

Data Index: 761622 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.9072. Min Range: -0.9072

Max Act: 0.6012. Min Act: -0.0000

Data Index: 804295 (C4 (Web Text))

Max Activating Token Index: 277