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

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

Neuron 1730 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: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0002

Data Index: 469210 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1032. Min Act: -0.0002

Data Index: 631132 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0002

Data Index: 954122 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0988. Min Act: -0.0002

Data Index: 1274139 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1042516 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0906. Min Act: -0.0002

Data Index: 975770 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0951. Min Act: -0.0002

Data Index: 522305 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0835. Min Act: -0.0002

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0875. Min Act: -0.0002

Data Index: 420123 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0824. Min Act: -0.0002

Data Index: 725290 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0807. Min Act: -0.0002

Data Index: 385734 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1304842 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1071123 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0825. Min Act: -0.0002

Data Index: 227374 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0788. Min Act: -0.0002

Data Index: 712625 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0813. Min Act: -0.0002

Data Index: 169672 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0775. Min Act: -0.0002

Data Index: 416732 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0819. Min Act: -0.0002

Data Index: 585192 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0769. Min Act: -0.0002

Data Index: 761317 (C4 (Web Text))

Max Activating Token Index: 150

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0807. Min Act: -0.0002

Data Index: 236203 (C4 (Web Text))

Max Activating Token Index: 875