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

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

Neuron 4124 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1276. Min Act: -0.0001

Data Index: 1386835 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1475637 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1594944 (Python Code)

Max Activating Token Index: 2

Text #3

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1559064 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1633603 (Python Code)

Max Activating Token Index: 13

Text #5

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1193. Min Act: -0.0001

Data Index: 1504576 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1601005 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1550396 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1216. Min Act: -0.0002

Data Index: 1556798 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1451014 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1652690 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1454840 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1617732 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1371324 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1601150 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0002

Data Index: 1423524 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1503521 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1606117 (Python Code)

Max Activating Token Index: 15

Text #18

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1618848 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 0.1276. Min Range: -0.1276

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1598818 (Python Code)

Max Activating Token Index: 15