Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 600 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.2184. Min Act: -0.0002

Data Index: 840585 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1753. Min Act: -0.0002

Data Index: 1037219 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1420. Min Act: -0.0002

Data Index: 695849 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1451. Min Act: -0.0002

Data Index: 185153 (C4 (Web Text))

Max Activating Token Index: 149

Text #4

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1314437 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1278. Min Act: -0.0002

Data Index: 905776 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1452. Min Act: -0.0002

Data Index: 1167155 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1377. Min Act: -0.0002

Data Index: 489479 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1305. Min Act: -0.0002

Data Index: 238028 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1046542 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1261. Min Act: -0.0002

Data Index: 189592 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1259. Min Act: -0.0002

Data Index: 438102 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1118. Min Act: -0.0002

Data Index: 973906 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1162. Min Act: -0.0002

Data Index: 72455 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1312723 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1187. Min Act: -0.0002

Data Index: 678957 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1065. Min Act: -0.0002

Data Index: 899914 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1165. Min Act: -0.0002

Data Index: 188155 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1192. Min Act: -0.0002

Data Index: 700506 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.2184. Min Range: -0.2184

Max Act: 0.1322. Min Act: -0.0002

Data Index: 686667 (C4 (Web Text))

Max Activating Token Index: 74