Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 637 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.5302. Min Act: -0.0000

Data Index: 718092 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4810. Min Act: -0.0000

Data Index: 306579 (C4 (Web Text))

Max Activating Token Index: 608

Text #2

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.5154. Min Act: -0.0000

Data Index: 315092 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4734. Min Act: -0.0000

Data Index: 809988 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4427. Min Act: -0.0000

Data Index: 950820 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4162. Min Act: -0.0000

Data Index: 995171 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4365. Min Act: -0.0000

Data Index: 828715 (C4 (Web Text))

Max Activating Token Index: 537

Text #7

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4620. Min Act: -0.0000

Data Index: 644227 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3849. Min Act: -0.0000

Data Index: 954234 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3598. Min Act: -0.0000

Data Index: 570235 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3545. Min Act: -0.0000

Data Index: 414603 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3561. Min Act: -0.0000

Data Index: 482760 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1065480 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3564. Min Act: -0.0000

Data Index: 849743 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1261613 (C4 (Web Text))

Max Activating Token Index: 51

Text #15

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3690. Min Act: -0.0000

Data Index: 1046567 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3784. Min Act: -0.0000

Data Index: 657764 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3796. Min Act: -0.0000

Data Index: 540749 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1249885 (C4 (Web Text))

Max Activating Token Index: 257

Text #19

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3618. Min Act: -0.0000

Data Index: 303747 (C4 (Web Text))

Max Activating Token Index: 75