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

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

Neuron 3966 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.4027. Min Act: -0.0000

Data Index: 654326 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3340. Min Act: -0.0000

Data Index: 247867 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3569. Min Act: -0.0000

Data Index: 22055 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3211. Min Act: -0.0000

Data Index: 13944 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3026. Min Act: -0.0000

Data Index: 662271 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2868. Min Act: -0.0000

Data Index: 552706 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3068. Min Act: -0.0000

Data Index: 134740 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3119. Min Act: -0.0000

Data Index: 1147347 (C4 (Web Text))

Max Activating Token Index: 623

Text #8

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.3036. Min Act: -0.0000

Data Index: 917011 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1047589 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2940. Min Act: -0.0000

Data Index: 270288 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2917. Min Act: -0.0000

Data Index: 602957 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2881. Min Act: -0.0000

Data Index: 1137103 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2799. Min Act: -0.0000

Data Index: 801481 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1141326 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2507. Min Act: -0.0000

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2854. Min Act: -0.0000

Data Index: 1272 (C4 (Web Text))

Max Activating Token Index: 153

Text #17

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1038339 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2671. Min Act: -0.0000

Data Index: 1166443 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.4027. Min Range: -0.4027

Max Act: 0.2633. Min Act: -0.0000

Data Index: 393850 (C4 (Web Text))

Max Activating Token Index: 418