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

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

Neuron 945 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: 0.1243. Min Range: -0.1243

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1233724 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1180. Min Act: -0.0002

Data Index: 874282 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1135. Min Act: -0.0002

Data Index: 740262 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1115. Min Act: -0.0002

Data Index: 1243172 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1052864 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1062. Min Act: -0.0002

Data Index: 75747 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1053. Min Act: -0.0002

Data Index: 166971 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1004. Min Act: -0.0002

Data Index: 888291 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1061. Min Act: -0.0002

Data Index: 991422 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1056477 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1004. Min Act: -0.0002

Data Index: 812042 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0980. Min Act: -0.0002

Data Index: 431060 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0958. Min Act: -0.0002

Data Index: 63317 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0981. Min Act: -0.0002

Data Index: 116073 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1200409 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0947. Min Act: -0.0002

Data Index: 313715 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.1021. Min Act: -0.0002

Data Index: 318295 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0990. Min Act: -0.0002

Data Index: 451777 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0965. Min Act: -0.0002

Data Index: 857207 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.1243. Min Range: -0.1243

Max Act: 0.0947. Min Act: -0.0002

Data Index: 453701 (C4 (Web Text))

Max Activating Token Index: 286