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

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

Neuron 3198 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1680. Min Act: -0.0000

Data Index: 306491 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1344. Min Act: -0.0000

Data Index: 166696 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1172037 (C4 (Web Text))

Max Activating Token Index: 311

Text #3

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1346. Min Act: -0.0000

Data Index: 308327 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1202714 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1156. Min Act: -0.0000

Data Index: 706417 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1192. Min Act: -0.0000

Data Index: 286600 (C4 (Web Text))

Max Activating Token Index: 62

Text #7

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1228. Min Act: -0.0000

Data Index: 64991 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1158. Min Act: -0.0000

Data Index: 462504 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1173. Min Act: -0.0000

Data Index: 1277019 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1130. Min Act: -0.0000

Data Index: 602313 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1161. Min Act: -0.0000

Data Index: 932178 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1006686 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1086. Min Act: -0.0000

Data Index: 702036 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1091. Min Act: -0.0000

Data Index: 452995 (C4 (Web Text))

Max Activating Token Index: 228

Text #15

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1028. Min Act: -0.0000

Data Index: 267855 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1074. Min Act: -0.0000

Data Index: 159080 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1042. Min Act: -0.0000

Data Index: 93831 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1064. Min Act: -0.0000

Data Index: 951008 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.1680. Min Range: -0.1680

Max Act: 0.1014. Min Act: -0.0000

Data Index: 639789 (C4 (Web Text))

Max Activating Token Index: 207