Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3836 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.1771. Min Act: -0.0003

Data Index: 242858 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.1708. Min Act: -0.0003

Data Index: 766180 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0792. Min Act: -0.0003

Data Index: 915303 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0645. Min Act: -0.0003

Data Index: 1195049 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.1771. Min Range: -1.1771

Max Act: 1.0636. Min Act: -0.0002

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9796. Min Act: -0.0002

Data Index: 1299536 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9673. Min Act: -0.0003

Data Index: 1189654 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9305. Min Act: -0.0002

Data Index: 154630 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9561. Min Act: -0.0003

Data Index: 127752 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9778. Min Act: -0.0003

Data Index: 942664 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9841. Min Act: -0.0003

Data Index: 59018 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9784. Min Act: -0.0003

Data Index: 998771 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9250. Min Act: -0.0003

Data Index: 216746 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9212. Min Act: -0.0003

Data Index: 414025 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9308. Min Act: -0.0002

Data Index: 1089851 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.8974. Min Act: -0.0002

Data Index: 668892 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9192. Min Act: -0.0003

Data Index: 641094 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9196. Min Act: -0.0003

Data Index: 913813 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9188. Min Act: -0.0002

Data Index: 829807 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 1.1771. Min Range: -1.1771

Max Act: 0.9149. Min Act: -0.0003

Data Index: 811510 (C4 (Web Text))

Max Activating Token Index: 374