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

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

Neuron 1823 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: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0002

Data Index: 607442 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1270779 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1298464 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0841. Min Act: -0.0002

Data Index: 674032 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0776. Min Act: -0.0002

Data Index: 393534 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0788. Min Act: -0.0002

Data Index: 828404 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0796. Min Act: -0.0002

Data Index: 70922 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1358840 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0784. Min Act: -0.0002

Data Index: 270736 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0758. Min Act: -0.0002

Data Index: 875630 (C4 (Web Text))

Max Activating Token Index: 812

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0758. Min Act: -0.0002

Data Index: 570932 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0747. Min Act: -0.0002

Data Index: 124303 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0731. Min Act: -0.0002

Data Index: 575152 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0738. Min Act: -0.0002

Data Index: 853444 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0722. Min Act: -0.0002

Data Index: 301027 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1085872 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0724. Min Act: -0.0001

Data Index: 371723 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0700. Min Act: -0.0002

Data Index: 614927 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0735. Min Act: -0.0002

Data Index: 508615 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1193539 (C4 (Web Text))

Max Activating Token Index: 864