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

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

Neuron 622 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: 0.1210. Min Range: -0.1210

Max Act: 0.1210. Min Act: -0.0002

Data Index: 641094 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.1076. Min Act: -0.0002

Data Index: 1140206 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0919. Min Act: -0.0002

Data Index: 247075 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0972. Min Act: -0.0001

Data Index: 134371 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0969. Min Act: -0.0002

Data Index: 858972 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1307974 (C4 (Web Text))

Max Activating Token Index: 276

Text #6

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1272043 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0939. Min Act: -0.0002

Data Index: 857161 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0978. Min Act: -0.0002

Data Index: 624980 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0948. Min Act: -0.0001

Data Index: 225280 (C4 (Web Text))

Max Activating Token Index: 226

Text #10

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0901. Min Act: -0.0002

Data Index: 590917 (C4 (Web Text))

Max Activating Token Index: 591

Text #11

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0932. Min Act: -0.0001

Data Index: 672310 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0913. Min Act: -0.0002

Data Index: 280871 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0935. Min Act: -0.0001

Data Index: 266195 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0913. Min Act: -0.0002

Data Index: 279991 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0859. Min Act: -0.0002

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0880. Min Act: -0.0002

Data Index: 701161 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1124842 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0865. Min Act: -0.0002

Data Index: 308874 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 0.1210. Min Range: -0.1210

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 335