Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 792 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1865. Min Act: -0.0002

Data Index: 812790 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1377. Min Act: -0.0002

Data Index: 724914 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1030. Min Act: -0.0002

Data Index: 814717 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1163. Min Act: -0.0002

Data Index: 856558 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1010. Min Act: -0.0002

Data Index: 1320588 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.1008. Min Act: -0.0002

Data Index: 469716 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0684. Min Act: -0.0002

Data Index: 580740 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0637. Min Act: -0.0002

Data Index: 635442 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0717. Min Act: -0.0002

Data Index: 82951 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0570. Min Act: -0.0002

Data Index: 630293 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0632. Min Act: -0.0002

Data Index: 649046 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0447. Min Act: -0.0002

Data Index: 707139 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0308. Min Act: -0.0002

Data Index: 1229182 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0329. Min Act: -0.0003

Data Index: 518482 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0056. Min Act: -0.0002

Data Index: 1076681 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0021. Min Act: -0.0002

Data Index: 482033 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0114. Min Act: -0.0002

Data Index: 991337 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9922. Min Act: -0.0002

Data Index: 407493 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 1.1865. Min Range: -1.1865

Max Act: 0.9869. Min Act: -0.0002

Data Index: 1033208 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.1865. Min Range: -1.1865

Max Act: 1.0037. Min Act: -0.0002

Data Index: 1209788 (C4 (Web Text))

Max Activating Token Index: 659