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

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

Neuron 685 in Layer 8

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: 746414 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4768. Min Act: -0.0000

Data Index: 421336 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4348. Min Act: -0.0000

Data Index: 388066 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4447. Min Act: -0.0000

Data Index: 957916 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1071971 (C4 (Web Text))

Max Activating Token Index: 832

Text #5

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4774. Min Act: -0.0000

Data Index: 547708 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4590. Min Act: -0.0000

Data Index: 506814 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4588. Min Act: -0.0000

Data Index: 1086672 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4376. Min Act: -0.0000

Data Index: 917502 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4354. Min Act: 0.0000

Data Index: 448972 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4075. Min Act: -0.0000

Data Index: 316976 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3762. Min Act: -0.0000

Data Index: 209945 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4003. Min Act: -0.0000

Data Index: 12739 (C4 (Web Text))

Max Activating Token Index: 658

Text #13

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4316. Min Act: -0.0000

Data Index: 1193453 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4191. Min Act: -0.0000

Data Index: 1094153 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3769. Min Act: -0.0000

Data Index: 220597 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3803. Min Act: -0.0000

Data Index: 969243 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.4145. Min Act: -0.0000

Data Index: 1299286 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3900. Min Act: -0.0000

Data Index: 4197 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 0.5302. Min Range: -0.5302

Max Act: 0.3878. Min Act: -0.0000

Data Index: 552971 (C4 (Web Text))

Max Activating Token Index: 500