Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3199 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.4185. Min Act: -0.0001

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 660

Text #1

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1868. Min Act: -0.0000

Data Index: 875760 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1883. Min Act: -0.0001

Data Index: 234239 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.2677. Min Act: -0.0000

Data Index: 1277814 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1597. Min Act: -0.0001

Data Index: 648590 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1926. Min Act: -0.0001

Data Index: 1027801 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1361. Min Act: -0.0001

Data Index: 290492 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1301. Min Act: -0.0001

Data Index: 813559 (C4 (Web Text))

Max Activating Token Index: 61

Text #8

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0686. Min Act: -0.0001

Data Index: 1352709 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1711. Min Act: -0.0001

Data Index: 830014 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0776. Min Act: -0.0001

Data Index: 1211307 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1103219 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1078. Min Act: -0.0001

Data Index: 128009 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0628. Min Act: -0.0000

Data Index: 985721 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1066. Min Act: -0.0001

Data Index: 806414 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0749. Min Act: -0.0000

Data Index: 732346 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0937. Min Act: -0.0001

Data Index: 1284295 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.1172. Min Act: -0.0001

Data Index: 810116 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0100. Min Act: -0.0001

Data Index: 1333884 (C4 (Web Text))

Max Activating Token Index: 214

Text #19

Max Range: 1.4185. Min Range: -1.4185

Max Act: 1.0528. Min Act: -0.0001

Data Index: 1194116 (C4 (Web Text))

Max Activating Token Index: 218