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

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

Neuron 3929 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.4753. Min Act: -0.0001

Data Index: 1205881 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.2732. Min Act: -0.0001

Data Index: 193561 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.4454. Min Act: -0.0001

Data Index: 1196223 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.3269. Min Act: -0.0001

Data Index: 710449 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.3599. Min Act: -0.0001

Data Index: 1152427 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.3159. Min Act: -0.0001

Data Index: 856605 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.2941. Min Act: -0.0001

Data Index: 671753 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.3673. Min Act: -0.0001

Data Index: 853704 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1960. Min Act: -0.0001

Data Index: 1193828 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1686. Min Act: -0.0001

Data Index: 319667 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1572. Min Act: -0.0001

Data Index: 85976 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1122. Min Act: -0.0001

Data Index: 1136436 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1596. Min Act: -0.0001

Data Index: 1027845 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1260. Min Act: -0.0001

Data Index: 1104040 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1136. Min Act: -0.0001

Data Index: 88121 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1298. Min Act: -0.0001

Data Index: 970016 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.2264. Min Act: -0.0001

Data Index: 858029 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.0845. Min Act: -0.0001

Data Index: 102541 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1689. Min Act: -0.0001

Data Index: 347348 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.4753. Min Range: -1.4753

Max Act: 1.1058. Min Act: -0.0001

Data Index: 190992 (C4 (Web Text))

Max Activating Token Index: 433