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

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

Neuron 799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1121. Min Act: -0.0005

Data Index: 503379 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1082. Min Act: -0.0005

Data Index: 901925 (C4 (Web Text))

Max Activating Token Index: 188

Text #2

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1024. Min Act: -0.0005

Data Index: 1285495 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1077. Min Act: -0.0005

Data Index: 257183 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1001. Min Act: -0.0005

Data Index: 715598 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1033. Min Act: -0.0005

Data Index: 708565 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0987. Min Act: -0.0005

Data Index: 933194 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0974. Min Act: -0.0005

Data Index: 812439 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0988. Min Act: -0.0005

Data Index: 1007209 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0988. Min Act: -0.0005

Data Index: 329016 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0934. Min Act: -0.0005

Data Index: 253137 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.1005. Min Act: -0.0005

Data Index: 306911 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0985. Min Act: -0.0005

Data Index: 768164 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0903. Min Act: -0.0005

Data Index: 254888 (C4 (Web Text))

Max Activating Token Index: 340

Text #14

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0902. Min Act: -0.0005

Data Index: 874004 (C4 (Web Text))

Max Activating Token Index: 137

Text #15

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0897. Min Act: -0.0005

Data Index: 734898 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0978. Min Act: -0.0005

Data Index: 1335498 (C4 (Web Text))

Max Activating Token Index: 578

Text #17

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0897. Min Act: -0.0005

Data Index: 528791 (C4 (Web Text))

Max Activating Token Index: 423

Text #18

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0890. Min Act: -0.0005

Data Index: 889794 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.1121. Min Range: -0.1121

Max Act: 0.0887. Min Act: -0.0005

Data Index: 421137 (C4 (Web Text))

Max Activating Token Index: 258