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

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

Neuron 1 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.4327. Min Act: -0.0001

Data Index: 427783 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1024187 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3869. Min Act: -0.0001

Data Index: 868339 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3578. Min Act: 0.0000

Data Index: 831711 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1022851 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3428. Min Act: -0.0001

Data Index: 1625561 (Python Code)

Max Activating Token Index: 175

Text #6

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3494. Min Act: -0.0001

Data Index: 864134 (C4 (Web Text))

Max Activating Token Index: 602

Text #7

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3350. Min Act: -0.0000

Data Index: 227045 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3336. Min Act: -0.0000

Data Index: 1063291 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3180. Min Act: 0.0001

Data Index: 1112845 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3274. Min Act: -0.0001

Data Index: 384084 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3138. Min Act: -0.0000

Data Index: 1027863 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3223. Min Act: -0.0000

Data Index: 458823 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3093. Min Act: -0.0001

Data Index: 1450264 (Python Code)

Max Activating Token Index: 230

Text #14

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3093. Min Act: -0.0000

Data Index: 310203 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3150. Min Act: -0.0001

Data Index: 791593 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3133. Min Act: -0.0001

Data Index: 24536 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3129. Min Act: -0.0000

Data Index: 108596 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.3051. Min Act: -0.0000

Data Index: 788683 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 0.4327. Min Range: -0.4327

Max Act: 0.2689. Min Act: 0.0001

Data Index: 849294 (C4 (Web Text))

Max Activating Token Index: 246