Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3875 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 10.0209. Min Range: -10.0209

Max Act: 10.0209. Min Act: -0.0001

Data Index: 1138943 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 10.0209. Min Range: -10.0209

Max Act: 9.8516. Min Act: -0.0001

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 10.0209. Min Range: -10.0209

Max Act: 9.6720. Min Act: -0.0001

Data Index: 75443 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 10.0209. Min Range: -10.0209

Max Act: 9.5166. Min Act: -0.0001

Data Index: 761498 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 10.0209. Min Range: -10.0209

Max Act: 9.1295. Min Act: -0.0001

Data Index: 514454 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.8302. Min Act: -0.0001

Data Index: 512660 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 10.0209. Min Range: -10.0209

Max Act: 9.0871. Min Act: -0.0001

Data Index: 51420 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.8875. Min Act: -0.0001

Data Index: 64007 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.9572. Min Act: -0.0001

Data Index: 455494 (C4 (Web Text))

Max Activating Token Index: 26

Text #9

Max Range: 10.0209. Min Range: -10.0209

Max Act: 9.0181. Min Act: -0.0001

Data Index: 631073 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.6396. Min Act: -0.0001

Data Index: 805 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.7536. Min Act: -0.0001

Data Index: 857778 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.5788. Min Act: -0.0001

Data Index: 931670 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.6683. Min Act: -0.0001

Data Index: 37475 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.4910. Min Act: -0.0001

Data Index: 1332804 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.5945. Min Act: -0.0001

Data Index: 638974 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.4522. Min Act: -0.0001

Data Index: 1045735 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.8491. Min Act: -0.0001

Data Index: 1049765 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.5529. Min Act: -0.0001

Data Index: 410992 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 10.0209. Min Range: -10.0209

Max Act: 8.3818. Min Act: -0.0001

Data Index: 999429 (C4 (Web Text))

Max Activating Token Index: 30