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

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

Neuron 2254 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: 1.4208. Min Range: -1.4208

Max Act: 1.2519. Min Act: -0.0001

Data Index: 231734 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.2146. Min Act: -0.0001

Data Index: 1261015 (C4 (Web Text))

Max Activating Token Index: 5

Text #2

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.4208. Min Act: -0.0001

Data Index: 1308668 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1912. Min Act: -0.0001

Data Index: 942755 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.2286. Min Act: -0.0001

Data Index: 156744 (C4 (Web Text))

Max Activating Token Index: 24

Text #5

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.2109. Min Act: -0.0001

Data Index: 76302 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1249. Min Act: -0.0001

Data Index: 1146371 (C4 (Web Text))

Max Activating Token Index: 236

Text #7

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1286725 (C4 (Web Text))

Max Activating Token Index: 187

Text #8

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.0686. Min Act: -0.0001

Data Index: 1291145 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1672. Min Act: -0.0001

Data Index: 1297684 (C4 (Web Text))

Max Activating Token Index: 503

Text #10

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1011. Min Act: -0.0001

Data Index: 1072450 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1072. Min Act: -0.0001

Data Index: 1001682 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1403. Min Act: -0.0001

Data Index: 557389 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1035. Min Act: -0.0001

Data Index: 1086055 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1664. Min Act: -0.0001

Data Index: 677168 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1430. Min Act: -0.0001

Data Index: 391576 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.0089. Min Act: -0.0001

Data Index: 72480 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1267. Min Act: -0.0001

Data Index: 82442 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.1103. Min Act: -0.0001

Data Index: 192194 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 1.4208. Min Range: -1.4208

Max Act: 1.0777. Min Act: -0.0001

Data Index: 25318 (C4 (Web Text))

Max Activating Token Index: 178