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

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

Neuron 1575 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: 0.1040. Min Range: -0.1040

Max Act: 0.1020. Min Act: -0.0005

Data Index: 746493 (C4 (Web Text))

Max Activating Token Index: 597

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0005

Data Index: 395704 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0989. Min Act: -0.0005

Data Index: 533877 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1000. Min Act: -0.0005

Data Index: 152905 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0962. Min Act: -0.0005

Data Index: 15662 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0945. Min Act: -0.0005

Data Index: 1124071 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0955. Min Act: -0.0005

Data Index: 425369 (C4 (Web Text))

Max Activating Token Index: 103

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0971. Min Act: -0.0005

Data Index: 209366 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0931. Min Act: -0.0005

Data Index: 799009 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0967. Min Act: -0.0005

Data Index: 1163142 (C4 (Web Text))

Max Activating Token Index: 179

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0941. Min Act: -0.0005

Data Index: 488734 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0993. Min Act: -0.0005

Data Index: 1067042 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0949. Min Act: -0.0005

Data Index: 478135 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0955. Min Act: -0.0005

Data Index: 32132 (C4 (Web Text))

Max Activating Token Index: 1022

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0972. Min Act: -0.0005

Data Index: 1341192 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0950. Min Act: -0.0005

Data Index: 1269821 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0915. Min Act: -0.0005

Data Index: 128833 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0944. Min Act: -0.0005

Data Index: 74852 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0924. Min Act: -0.0005

Data Index: 1147797 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0988. Min Act: -0.0005

Data Index: 1266649 (C4 (Web Text))

Max Activating Token Index: 640