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

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

Neuron 4609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0163. Min Range: -2.0163

Max Act: 2.0163. Min Act: -0.0000

Data Index: 515900 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.6460. Min Act: -0.0000

Data Index: 227996 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.3490. Min Act: -0.0000

Data Index: 345247 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.4240. Min Act: -0.0000

Data Index: 41726 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.3228. Min Act: -0.0000

Data Index: 941082 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.3580. Min Act: -0.0000

Data Index: 902924 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1123375 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.3493. Min Act: -0.0000

Data Index: 635724 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.3693. Min Act: -0.0000

Data Index: 468472 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.2885. Min Act: -0.0000

Data Index: 1149862 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.2491. Min Act: -0.0000

Data Index: 404571 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.2630. Min Act: -0.0000

Data Index: 455896 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.2250. Min Act: -0.0000

Data Index: 817266 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.1867. Min Act: -0.0000

Data Index: 465034 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.1865. Min Act: -0.0000

Data Index: 209232 (C4 (Web Text))

Max Activating Token Index: 187

Text #15

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.1920. Min Act: -0.0000

Data Index: 750997 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.2812. Min Act: -0.0000

Data Index: 307431 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.2123. Min Act: -0.0000

Data Index: 1333451 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.1370. Min Act: -0.0000

Data Index: 211275 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 2.0163. Min Range: -2.0163

Max Act: 1.1806. Min Act: -0.0000

Data Index: 115165 (C4 (Web Text))

Max Activating Token Index: 524