Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3791 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1224. Min Act: -0.0001

Data Index: 144361 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1278. Min Act: -0.0001

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1212. Min Act: -0.0000

Data Index: 942159 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1109. Min Act: -0.0001

Data Index: 840263 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1115. Min Act: -0.0001

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1188. Min Act: -0.0001

Data Index: 315944 (C4 (Web Text))

Max Activating Token Index: 117

Text #6

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1075. Min Act: -0.0000

Data Index: 43651 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1134. Min Act: -0.0001

Data Index: 937748 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1110. Min Act: -0.0000

Data Index: 764291 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1103. Min Act: -0.0001

Data Index: 322244 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1101. Min Act: -0.0000

Data Index: 131578 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1096. Min Act: -0.0001

Data Index: 980779 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1054. Min Act: -0.0001

Data Index: 93958 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1043. Min Act: -0.0001

Data Index: 106978 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1045. Min Act: -0.0001

Data Index: 370114 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1163. Min Act: -0.0001

Data Index: 482769 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1042. Min Act: -0.0000

Data Index: 423870 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1072. Min Act: -0.0000

Data Index: 619578 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1069. Min Act: -0.0000

Data Index: 504527 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1278. Min Range: -0.1278

Max Act: 0.1005. Min Act: -0.0001

Data Index: 755958 (C4 (Web Text))

Max Activating Token Index: 419