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

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

Neuron 5639 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.7521. Min Act: -0.0000

Data Index: 731199 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1285224 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5810. Min Act: -0.0000

Data Index: 290418 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5365. Min Act: -0.0000

Data Index: 787993 (C4 (Web Text))

Max Activating Token Index: 45

Text #4

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5392. Min Act: -0.0000

Data Index: 712402 (C4 (Web Text))

Max Activating Token Index: 882

Text #5

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5423. Min Act: -0.0000

Data Index: 1158790 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5196. Min Act: -0.0000

Data Index: 329978 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.5151. Min Act: -0.0000

Data Index: 24238 (C4 (Web Text))

Max Activating Token Index: 1002

Text #8

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1246451 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4820. Min Act: -0.0000

Data Index: 125005 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4962. Min Act: -0.0000

Data Index: 160179 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4922. Min Act: -0.0000

Data Index: 294041 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1312497 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4668. Min Act: -0.0000

Data Index: 672086 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4690. Min Act: -0.0000

Data Index: 744705 (C4 (Web Text))

Max Activating Token Index: 522

Text #15

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4993. Min Act: -0.0000

Data Index: 205628 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4802. Min Act: -0.0000

Data Index: 949922 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4660. Min Act: -0.0000

Data Index: 919698 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4623. Min Act: -0.0000

Data Index: 652679 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.7521. Min Range: -0.7521

Max Act: 0.4749. Min Act: -0.0000

Data Index: 237221 (C4 (Web Text))

Max Activating Token Index: 192