Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0003

Data Index: 1196244 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0832. Min Act: -0.0003

Data Index: 614825 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0003

Data Index: 25937 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0823. Min Act: -0.0003

Data Index: 314356 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0809. Min Act: -0.0003

Data Index: 259682 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0807. Min Act: -0.0003

Data Index: 1173368 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0808. Min Act: -0.0003

Data Index: 964327 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0796. Min Act: -0.0003

Data Index: 1339252 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0782. Min Act: -0.0003

Data Index: 251634 (C4 (Web Text))

Max Activating Token Index: 77

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0799. Min Act: -0.0003

Data Index: 806837 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0784. Min Act: -0.0003

Data Index: 387858 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0783. Min Act: -0.0003

Data Index: 602431 (C4 (Web Text))

Max Activating Token Index: 295

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0761. Min Act: -0.0003

Data Index: 368142 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0769. Min Act: -0.0002

Data Index: 859488 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0779. Min Act: -0.0003

Data Index: 905499 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0765. Min Act: -0.0003

Data Index: 272219 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1254838 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0733. Min Act: -0.0004

Data Index: 333448 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1246062 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0731. Min Act: -0.0003

Data Index: 807724 (C4 (Web Text))

Max Activating Token Index: 133