Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 676 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4699. Min Act: -0.0003

Data Index: 978625 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4675. Min Act: -0.0003

Data Index: 870770 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4650. Min Act: -0.0003

Data Index: 944397 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4297. Min Act: -0.0003

Data Index: 182252 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4439. Min Act: -0.0003

Data Index: 1145270 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.4375. Min Act: -0.0002

Data Index: 56545 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3954. Min Act: -0.0003

Data Index: 1109633 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3778. Min Act: -0.0003

Data Index: 40367 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3669. Min Act: -0.0003

Data Index: 591206 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3607. Min Act: -0.0003

Data Index: 738977 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3579. Min Act: -0.0002

Data Index: 84501 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3488. Min Act: -0.0003

Data Index: 1112094 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3477. Min Act: -0.0003

Data Index: 132097 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3446. Min Act: -0.0003

Data Index: 232022 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3382. Min Act: -0.0003

Data Index: 1349372 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3305. Min Act: -0.0003

Data Index: 1358937 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3301. Min Act: -0.0003

Data Index: 225226 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3277. Min Act: -0.0002

Data Index: 740576 (C4 (Web Text))

Max Activating Token Index: 718

Text #18

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3237. Min Act: -0.0003

Data Index: 1230009 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.4699. Min Range: -0.4699

Max Act: 0.3194. Min Act: -0.0003

Data Index: 843009 (C4 (Web Text))

Max Activating Token Index: 738