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

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

Neuron 3505 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.5228. Min Act: -0.0000

Data Index: 1546962 (Python Code)

Max Activating Token Index: 705

Text #1

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.2678. Min Act: -0.0000

Data Index: 1616228 (Python Code)

Max Activating Token Index: 394

Text #2

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.0221. Min Act: -0.0000

Data Index: 1566677 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 4.5228. Min Range: -4.5228

Max Act: 4.1902. Min Act: -0.0000

Data Index: 1467178 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.8806. Min Act: -0.0000

Data Index: 1404956 (Python Code)

Max Activating Token Index: 53

Text #5

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.8064. Min Act: -0.0000

Data Index: 1538793 (Python Code)

Max Activating Token Index: 160

Text #6

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.7969. Min Act: -0.0000

Data Index: 1376714 (Python Code)

Max Activating Token Index: 236

Text #7

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.4163. Min Act: -0.0000

Data Index: 1543248 (Python Code)

Max Activating Token Index: 598

Text #8

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.7076. Min Act: -0.0000

Data Index: 1609987 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.5575. Min Act: -0.0000

Data Index: 1525885 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.6862. Min Act: -0.0000

Data Index: 1503499 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.5962. Min Act: -0.0000

Data Index: 1595908 (Python Code)

Max Activating Token Index: 155

Text #12

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.3898. Min Act: -0.0000

Data Index: 1432897 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.5496. Min Act: -0.0000

Data Index: 1408246 (Python Code)

Max Activating Token Index: 208

Text #14

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.5054. Min Act: -0.0000

Data Index: 1535862 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.4941. Min Act: -0.0000

Data Index: 1366108 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.4986. Min Act: -0.0000

Data Index: 1651301 (Python Code)

Max Activating Token Index: 110

Text #17

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.6359. Min Act: -0.0000

Data Index: 1486401 (Python Code)

Max Activating Token Index: 514

Text #18

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.4700. Min Act: -0.0000

Data Index: 1562688 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 4.5228. Min Range: -4.5228

Max Act: 3.4512. Min Act: -0.0000

Data Index: 1655170 (Python Code)

Max Activating Token Index: 966