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

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

Neuron 526 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: 0.1425. Min Range: -0.1425

Max Act: 0.1425. Min Act: -0.0002

Data Index: 689984 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1379. Min Act: -0.0002

Data Index: 357242 (C4 (Web Text))

Max Activating Token Index: 760

Text #2

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1200. Min Act: -0.0002

Data Index: 1165406 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1167. Min Act: -0.0002

Data Index: 791659 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1149. Min Act: -0.0002

Data Index: 748969 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1148. Min Act: -0.0002

Data Index: 337458 (C4 (Web Text))

Max Activating Token Index: 176

Text #6

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1156. Min Act: -0.0002

Data Index: 828133 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1114. Min Act: -0.0002

Data Index: 200810 (C4 (Web Text))

Max Activating Token Index: 221

Text #8

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1117. Min Act: -0.0002

Data Index: 442633 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1137. Min Act: -0.0002

Data Index: 9774 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1092. Min Act: -0.0002

Data Index: 33265 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1119431 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1211019 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1075. Min Act: -0.0002

Data Index: 1206725 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1086. Min Act: -0.0002

Data Index: 843129 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1078. Min Act: -0.0002

Data Index: 1076226 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1068. Min Act: -0.0002

Data Index: 975183 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1068. Min Act: -0.0002

Data Index: 95404 (C4 (Web Text))

Max Activating Token Index: 18

Text #18

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1062. Min Act: -0.0002

Data Index: 239397 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.1425. Min Range: -0.1425

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1048614 (C4 (Web Text))

Max Activating Token Index: 828