Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1547 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.1272. Min Act: -0.0003

Data Index: 989740 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0924. Min Act: -0.0003

Data Index: 197782 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0877. Min Act: -0.0003

Data Index: 2169 (C4 (Web Text))

Max Activating Token Index: 197

Text #3

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0830. Min Act: -0.0003

Data Index: 641120 (C4 (Web Text))

Max Activating Token Index: 303

Text #4

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0858. Min Act: -0.0003

Data Index: 1055290 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0814. Min Act: -0.0003

Data Index: 71057 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0813. Min Act: -0.0003

Data Index: 213749 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0788. Min Act: -0.0003

Data Index: 626250 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0801. Min Act: -0.0003

Data Index: 58270 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0764. Min Act: -0.0003

Data Index: 722300 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0729. Min Act: -0.0003

Data Index: 873372 (C4 (Web Text))

Max Activating Token Index: 426

Text #11

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0741. Min Act: -0.0003

Data Index: 85414 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0739. Min Act: -0.0003

Data Index: 65673 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1086165 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0784. Min Act: -0.0003

Data Index: 164741 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1048366 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0770. Min Act: -0.0003

Data Index: 912152 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0728. Min Act: -0.0003

Data Index: 55020 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0722. Min Act: -0.0003

Data Index: 704722 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.1272. Min Range: -0.1272

Max Act: 0.0758. Min Act: -0.0003

Data Index: 260917 (C4 (Web Text))

Max Activating Token Index: 363