Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 898 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1196292 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2668. Min Act: -0.0000

Data Index: 296173 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2586. Min Act: -0.0000

Data Index: 88136 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2120. Min Act: -0.0000

Data Index: 237832 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1273607 (C4 (Web Text))

Max Activating Token Index: 415

Text #5

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2331. Min Act: -0.0000

Data Index: 558522 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2312. Min Act: -0.0000

Data Index: 592828 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2486. Min Act: -0.0000

Data Index: 1192710 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1117231 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1509. Min Act: -0.0000

Data Index: 735370 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1179299 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1432. Min Act: -0.0000

Data Index: 949897 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1994. Min Act: -0.0000

Data Index: 1028307 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1675. Min Act: -0.0000

Data Index: 306976 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1261. Min Act: -0.0000

Data Index: 35584 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1959. Min Act: -0.0000

Data Index: 709470 (C4 (Web Text))

Max Activating Token Index: 81

Text #16

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1614. Min Act: -0.0000

Data Index: 237223 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1549. Min Act: -0.0000

Data Index: 907722 (C4 (Web Text))

Max Activating Token Index: 356

Text #18

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1544. Min Act: -0.0000

Data Index: 4030 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 1.4580. Min Range: -1.4580

Max Act: 1.1769. Min Act: -0.0000

Data Index: 263412 (C4 (Web Text))

Max Activating Token Index: 86