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

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

Neuron 2347 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: 0.3433. Min Range: -0.3433

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1331933 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3172. Min Act: -0.0000

Data Index: 309039 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3236. Min Act: -0.0000

Data Index: 561640 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3080. Min Act: -0.0000

Data Index: 119893 (C4 (Web Text))

Max Activating Token Index: 304

Text #4

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3095. Min Act: -0.0000

Data Index: 1286857 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2653. Min Act: -0.0000

Data Index: 712738 (C4 (Web Text))

Max Activating Token Index: 956

Text #6

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1234315 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1084362 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1027098 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3045. Min Act: -0.0000

Data Index: 791600 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2954. Min Act: -0.0000

Data Index: 926440 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3104. Min Act: -0.0000

Data Index: 912880 (C4 (Web Text))

Max Activating Token Index: 399

Text #12

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1147643 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1077501 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2877. Min Act: -0.0000

Data Index: 1065590 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.3111. Min Act: -0.0000

Data Index: 310665 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1259649 (C4 (Web Text))

Max Activating Token Index: 924

Text #17

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2704. Min Act: -0.0000

Data Index: 647670 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2956. Min Act: -0.0000

Data Index: 1328673 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.3433. Min Range: -0.3433

Max Act: 0.2692. Min Act: -0.0000

Data Index: 359595 (C4 (Web Text))

Max Activating Token Index: 271