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

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

Neuron 1309 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.3047. Min Act: -0.0001

Data Index: 1434613 (Python Code)

Max Activating Token Index: 159

Text #1

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.2497. Min Act: -0.0001

Data Index: 1448288 (Python Code)

Max Activating Token Index: 552

Text #2

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1360. Min Act: -0.0001

Data Index: 1449403 (Python Code)

Max Activating Token Index: 757

Text #3

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1326. Min Act: -0.0001

Data Index: 1620610 (Python Code)

Max Activating Token Index: 366

Text #4

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1431. Min Act: -0.0001

Data Index: 1563785 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1567357 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1418486 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1222. Min Act: -0.0001

Data Index: 1365961 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1542852 (Python Code)

Max Activating Token Index: 168

Text #9

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1439466 (Python Code)

Max Activating Token Index: 277

Text #10

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1229. Min Act: -0.0001

Data Index: 1365142 (Python Code)

Max Activating Token Index: 560

Text #11

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1181. Min Act: -0.0001

Data Index: 1477381 (Python Code)

Max Activating Token Index: 95

Text #12

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1645353 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1475633 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1619188 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1536403 (Python Code)

Max Activating Token Index: 79

Text #16

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1187. Min Act: -0.0001

Data Index: 960905 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1139. Min Act: -0.0001

Data Index: 1571007 (Python Code)

Max Activating Token Index: 518

Text #18

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1435420 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.3047. Min Range: -0.3047

Max Act: 0.1187. Min Act: -0.0001

Data Index: 1652357 (Python Code)

Max Activating Token Index: 193