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

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

Neuron 1037 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2407. Min Range: -2.2407

Max Act: 2.2407. Min Act: -0.0000

Data Index: 1362003 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 2.2407. Min Range: -2.2407

Max Act: 2.1546. Min Act: -0.0000

Data Index: 1502538 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 2.2407. Min Range: -2.2407

Max Act: 2.0183. Min Act: -0.0000

Data Index: 1519421 (Python Code)

Max Activating Token Index: 256

Text #3

Max Range: 2.2407. Min Range: -2.2407

Max Act: 2.0662. Min Act: -0.0000

Data Index: 1506508 (Python Code)

Max Activating Token Index: 52

Text #4

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.9630. Min Act: -0.0000

Data Index: 1587977 (Python Code)

Max Activating Token Index: 115

Text #5

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.9972. Min Act: -0.0000

Data Index: 1452225 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.9144. Min Act: -0.0000

Data Index: 1427584 (Python Code)

Max Activating Token Index: 146

Text #7

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.9085. Min Act: -0.0000

Data Index: 1551354 (Python Code)

Max Activating Token Index: 164

Text #8

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.8151. Min Act: -0.0000

Data Index: 1451639 (Python Code)

Max Activating Token Index: 18

Text #9

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.8041. Min Act: -0.0000

Data Index: 1575590 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.8329. Min Act: -0.0000

Data Index: 1505932 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.8121. Min Act: -0.0000

Data Index: 1556420 (Python Code)

Max Activating Token Index: 55

Text #12

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.7500. Min Act: -0.0000

Data Index: 1381076 (Python Code)

Max Activating Token Index: 35

Text #13

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.6859. Min Act: -0.0000

Data Index: 1592110 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.6178. Min Act: -0.0000

Data Index: 1641452 (Python Code)

Max Activating Token Index: 184

Text #15

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.6607. Min Act: -0.0000

Data Index: 1651101 (Python Code)

Max Activating Token Index: 49

Text #16

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.7393. Min Act: -0.0000

Data Index: 1414611 (Python Code)

Max Activating Token Index: 43

Text #17

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.7247. Min Act: -0.0000

Data Index: 1639371 (Python Code)

Max Activating Token Index: 150

Text #18

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.7147. Min Act: -0.0000

Data Index: 1569982 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 2.2407. Min Range: -2.2407

Max Act: 1.5716. Min Act: -0.0000

Data Index: 1626313 (Python Code)

Max Activating Token Index: 86