Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1245 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1703. Min Act: -0.0001

Data Index: 720842 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1490. Min Act: -0.0001

Data Index: 1307176 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1340683 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1527. Min Act: -0.0001

Data Index: 152033 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1177234 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1214691 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1048308 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1398. Min Act: -0.0001

Data Index: 1128034 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1254. Min Act: -0.0001

Data Index: 1292559 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1387. Min Act: -0.0001

Data Index: 781916 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1382. Min Act: -0.0001

Data Index: 738126 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1435. Min Act: -0.0001

Data Index: 9375 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1329. Min Act: -0.0001

Data Index: 1275963 (C4 (Web Text))

Max Activating Token Index: 402

Text #13

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1318. Min Act: -0.0001

Data Index: 364507 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1329. Min Act: -0.0001

Data Index: 77370 (C4 (Web Text))

Max Activating Token Index: 121

Text #15

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1278. Min Act: -0.0001

Data Index: 550983 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1318. Min Act: -0.0001

Data Index: 963720 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1367. Min Act: -0.0001

Data Index: 79511 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1235. Min Act: -0.0001

Data Index: 690949 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1703. Min Range: -0.1703

Max Act: 0.1313. Min Act: -0.0001

Data Index: 95761 (C4 (Web Text))

Max Activating Token Index: 173