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

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

Neuron 1983 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1478. Min Act: -0.0006

Data Index: 398456 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1165. Min Act: -0.0006

Data Index: 922900 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1227. Min Act: -0.0006

Data Index: 1123848 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1164. Min Act: -0.0006

Data Index: 1186782 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1165. Min Act: -0.0006

Data Index: 859223 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1199. Min Act: -0.0006

Data Index: 531860 (C4 (Web Text))

Max Activating Token Index: 26

Text #6

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1062. Min Act: -0.0006

Data Index: 657996 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1131. Min Act: -0.0006

Data Index: 1143809 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1104. Min Act: -0.0006

Data Index: 686865 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1050. Min Act: -0.0006

Data Index: 55675 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1080. Min Act: -0.0006

Data Index: 1026299 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1070. Min Act: -0.0006

Data Index: 313130 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1097. Min Act: -0.0006

Data Index: 322174 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1054. Min Act: -0.0006

Data Index: 160336 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1053. Min Act: -0.0006

Data Index: 809058 (C4 (Web Text))

Max Activating Token Index: 898

Text #15

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1047. Min Act: -0.0006

Data Index: 615467 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1028. Min Act: -0.0006

Data Index: 1007703 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1015. Min Act: -0.0006

Data Index: 389297 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1099. Min Act: -0.0006

Data Index: 555251 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 0.1478. Min Range: -0.1478

Max Act: 0.1091. Min Act: -0.0006

Data Index: 271189 (C4 (Web Text))

Max Activating Token Index: 845