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

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

Neuron 4563 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: 0.7695. Min Range: -0.7695

Max Act: 0.7665. Min Act: -0.0002

Data Index: 472409 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7695. Min Act: -0.0002

Data Index: 425910 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7252. Min Act: -0.0002

Data Index: 445778 (C4 (Web Text))

Max Activating Token Index: 163

Text #3

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7054. Min Act: -0.0002

Data Index: 1020629 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6757. Min Act: -0.0002

Data Index: 61831 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6791. Min Act: -0.0002

Data Index: 886229 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6667. Min Act: -0.0002

Data Index: 648403 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6593. Min Act: -0.0002

Data Index: 347388 (C4 (Web Text))

Max Activating Token Index: 224

Text #8

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6344. Min Act: -0.0002

Data Index: 310064 (C4 (Web Text))

Max Activating Token Index: 1016

Text #9

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6518. Min Act: -0.0002

Data Index: 1157754 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6337. Min Act: -0.0002

Data Index: 768138 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6369. Min Act: -0.0002

Data Index: 249264 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6329. Min Act: -0.0002

Data Index: 1003796 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6201. Min Act: -0.0002

Data Index: 509868 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6293. Min Act: -0.0003

Data Index: 249159 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6277. Min Act: -0.0002

Data Index: 733556 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6221. Min Act: -0.0002

Data Index: 36769 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6160. Min Act: -0.0002

Data Index: 1214800 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6195. Min Act: -0.0002

Data Index: 59223 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6023. Min Act: -0.0002

Data Index: 516340 (C4 (Web Text))

Max Activating Token Index: 1016