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

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

Neuron 830 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5725. Min Act: -0.0001

Data Index: 40629 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5409. Min Act: -0.0001

Data Index: 762033 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5003. Min Act: -0.0001

Data Index: 902136 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4696. Min Act: -0.0001

Data Index: 655404 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4553. Min Act: -0.0001

Data Index: 1190332 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4285. Min Act: -0.0001

Data Index: 684571 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3961. Min Act: -0.0001

Data Index: 536872 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4397. Min Act: -0.0001

Data Index: 656422 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3920. Min Act: -0.0001

Data Index: 704476 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3669. Min Act: -0.0001

Data Index: 241585 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4158. Min Act: -0.0001

Data Index: 101374 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4033. Min Act: -0.0001

Data Index: 1357936 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4164. Min Act: -0.0001

Data Index: 97830 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1030847 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4092. Min Act: -0.0001

Data Index: 624076 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4148. Min Act: -0.0001

Data Index: 1251160 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3883. Min Act: -0.0001

Data Index: 249813 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4140. Min Act: -0.0001

Data Index: 1337905 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.3827. Min Act: -0.0001

Data Index: 596376 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4068. Min Act: -0.0001

Data Index: 476897 (C4 (Web Text))

Max Activating Token Index: 989