Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 129 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1271. Min Act: -0.0004

Data Index: 185076 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1281. Min Act: -0.0003

Data Index: 686822 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1261. Min Act: -0.0003

Data Index: 762506 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1182. Min Act: -0.0003

Data Index: 522037 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1150. Min Act: -0.0003

Data Index: 1094440 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1120. Min Act: -0.0003

Data Index: 1175374 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1125. Min Act: -0.0003

Data Index: 850066 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1174. Min Act: -0.0003

Data Index: 1165149 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1139. Min Act: -0.0003

Data Index: 1043035 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1112. Min Act: -0.0003

Data Index: 312767 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1157. Min Act: -0.0003

Data Index: 1329023 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1099. Min Act: -0.0003

Data Index: 906332 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1132. Min Act: -0.0003

Data Index: 837795 (C4 (Web Text))

Max Activating Token Index: 821

Text #13

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1086. Min Act: -0.0003

Data Index: 493044 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1094. Min Act: -0.0003

Data Index: 272691 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1094. Min Act: -0.0003

Data Index: 1336703 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1100. Min Act: -0.0003

Data Index: 646467 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1043. Min Act: -0.0003

Data Index: 1011362 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1044. Min Act: -0.0003

Data Index: 473189 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.1281. Min Range: -0.1281

Max Act: 0.1063. Min Act: -0.0003

Data Index: 391174 (C4 (Web Text))

Max Activating Token Index: 698