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

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

Neuron 1139 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: 0.1045. Min Range: -0.1045

Max Act: 0.1045. Min Act: -0.0002

Data Index: 990294 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.1025. Min Act: -0.0001

Data Index: 431975 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0995. Min Act: -0.0002

Data Index: 262 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0916. Min Act: -0.0002

Data Index: 485197 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0944. Min Act: -0.0002

Data Index: 476159 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0910. Min Act: -0.0002

Data Index: 842035 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0920. Min Act: -0.0002

Data Index: 216693 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0895. Min Act: -0.0002

Data Index: 311158 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0907. Min Act: -0.0002

Data Index: 425823 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0883. Min Act: -0.0002

Data Index: 440983 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0861. Min Act: -0.0002

Data Index: 432742 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1131607 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1089350 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1150808 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0822. Min Act: -0.0002

Data Index: 253817 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0826. Min Act: -0.0002

Data Index: 434691 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1290446 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0847. Min Act: -0.0002

Data Index: 944936 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1069882 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1045. Min Range: -0.1045

Max Act: 0.0847. Min Act: -0.0002

Data Index: 603011 (C4 (Web Text))

Max Activating Token Index: 487