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

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

Neuron 4193 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: 2.4239. Min Range: -2.4239

Max Act: 2.4239. Min Act: -0.0002

Data Index: 40843 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 2.4239. Min Range: -2.4239

Max Act: 2.0799. Min Act: -0.0002

Data Index: 768677 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 2.4239. Min Range: -2.4239

Max Act: 2.0600. Min Act: -0.0003

Data Index: 77635 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 2.4239. Min Range: -2.4239

Max Act: 2.0713. Min Act: -0.0002

Data Index: 654228 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 2.4239. Min Range: -2.4239

Max Act: 2.0790. Min Act: -0.0002

Data Index: 819516 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 2.4239. Min Range: -2.4239

Max Act: 2.0800. Min Act: -0.0002

Data Index: 412526 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.9777. Min Act: -0.0002

Data Index: 388972 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.9104. Min Act: -0.0002

Data Index: 74458 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.9032. Min Act: -0.0002

Data Index: 224328 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8563. Min Act: -0.0002

Data Index: 586698 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.9211. Min Act: -0.0002

Data Index: 1352163 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8745. Min Act: -0.0002

Data Index: 82670 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.9185. Min Act: -0.0002

Data Index: 818660 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8795. Min Act: -0.0002

Data Index: 1253099 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8063. Min Act: -0.0002

Data Index: 1158984 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8858. Min Act: -0.0002

Data Index: 304457 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8839. Min Act: -0.0002

Data Index: 992099 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8472. Min Act: -0.0002

Data Index: 1146146 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.8207. Min Act: -0.0002

Data Index: 15593 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.4239. Min Range: -2.4239

Max Act: 1.7996. Min Act: -0.0002

Data Index: 274422 (C4 (Web Text))

Max Activating Token Index: 74