Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 524 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1530. Min Act: -0.0003

Data Index: 444443 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1360. Min Act: -0.0003

Data Index: 882140 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1232. Min Act: -0.0003

Data Index: 1332501 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1266. Min Act: -0.0003

Data Index: 599372 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1297. Min Act: -0.0003

Data Index: 878778 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1189. Min Act: -0.0003

Data Index: 850910 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1220. Min Act: -0.0003

Data Index: 586036 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1160. Min Act: -0.0003

Data Index: 512997 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1188. Min Act: -0.0003

Data Index: 240300 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1107. Min Act: -0.0003

Data Index: 642788 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1079. Min Act: -0.0003

Data Index: 1143706 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1137. Min Act: -0.0003

Data Index: 1314777 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1139. Min Act: -0.0003

Data Index: 473571 (C4 (Web Text))

Max Activating Token Index: 170

Text #13

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1139. Min Act: -0.0004

Data Index: 791202 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1089. Min Act: -0.0003

Data Index: 816504 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1095. Min Act: -0.0003

Data Index: 255028 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1069. Min Act: -0.0002

Data Index: 527125 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1076. Min Act: -0.0003

Data Index: 948281 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1039. Min Act: -0.0003

Data Index: 541527 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.1530. Min Range: -0.1530

Max Act: 0.1035. Min Act: -0.0003

Data Index: 333674 (C4 (Web Text))

Max Activating Token Index: 217