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

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

Neuron 4828 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.1876. Min Act: -0.0000

Data Index: 204496 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.2372. Min Act: -0.0000

Data Index: 226166 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1212146 (C4 (Web Text))

Max Activating Token Index: 106

Text #3

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0790. Min Act: -0.0000

Data Index: 978382 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1192239 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1233185 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9885. Min Act: -0.0000

Data Index: 526102 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0789. Min Act: -0.0000

Data Index: 366274 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0600. Min Act: -0.0000

Data Index: 612151 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0393. Min Act: -0.0000

Data Index: 475860 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1165572 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 1.2372. Min Range: -1.2372

Max Act: 1.0208. Min Act: -0.0000

Data Index: 344273 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9800. Min Act: -0.0000

Data Index: 309994 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9816. Min Act: -0.0000

Data Index: 302575 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9711. Min Act: -0.0000

Data Index: 140392 (C4 (Web Text))

Max Activating Token Index: 488

Text #15

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1115196 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.8963. Min Act: -0.0000

Data Index: 8369 (C4 (Web Text))

Max Activating Token Index: 261

Text #17

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9499. Min Act: -0.0000

Data Index: 646982 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9143. Min Act: -0.0000

Data Index: 1210717 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 1.2372. Min Range: -1.2372

Max Act: 0.9577. Min Act: -0.0000

Data Index: 71022 (C4 (Web Text))

Max Activating Token Index: 994