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

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

Neuron 649 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: 0.1361. Min Range: -0.1361

Max Act: 0.1341. Min Act: -0.0002

Data Index: 1304390 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1361. Min Act: -0.0002

Data Index: 1184833 (C4 (Web Text))

Max Activating Token Index: 986

Text #2

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1180. Min Act: -0.0002

Data Index: 109471 (C4 (Web Text))

Max Activating Token Index: 673

Text #3

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1227. Min Act: -0.0002

Data Index: 117095 (C4 (Web Text))

Max Activating Token Index: 103

Text #4

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1097. Min Act: -0.0002

Data Index: 714392 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1133. Min Act: -0.0002

Data Index: 188187 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1102. Min Act: -0.0002

Data Index: 772936 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1136. Min Act: -0.0002

Data Index: 1236101 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1117. Min Act: -0.0002

Data Index: 136569 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1118. Min Act: -0.0002

Data Index: 1110317 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1069. Min Act: -0.0002

Data Index: 585269 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1016. Min Act: -0.0002

Data Index: 620904 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1107. Min Act: -0.0002

Data Index: 729574 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1076. Min Act: -0.0002

Data Index: 666275 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1015. Min Act: -0.0002

Data Index: 1081364 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1062. Min Act: -0.0002

Data Index: 955978 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1050. Min Act: -0.0002

Data Index: 530468 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1034. Min Act: -0.0002

Data Index: 287742 (C4 (Web Text))

Max Activating Token Index: 527

Text #18

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.1047. Min Act: -0.0002

Data Index: 1008318 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.1361. Min Range: -0.1361

Max Act: 0.0995. Min Act: -0.0002

Data Index: 96354 (C4 (Web Text))

Max Activating Token Index: 519