Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 830 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6447. Min Act: -0.0001

Data Index: 52736 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6317. Min Act: -0.0002

Data Index: 562268 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1288661 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5703. Min Act: -0.0001

Data Index: 974805 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6039. Min Act: -0.0001

Data Index: 390485 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.6212. Min Act: -0.0001

Data Index: 995067 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5191. Min Act: -0.0001

Data Index: 512349 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5566. Min Act: -0.0001

Data Index: 411167 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5673. Min Act: -0.0001

Data Index: 505739 (C4 (Web Text))

Max Activating Token Index: 481

Text #9

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5402. Min Act: -0.0001

Data Index: 580681 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5300. Min Act: -0.0001

Data Index: 1320796 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5305. Min Act: -0.0002

Data Index: 900528 (C4 (Web Text))

Max Activating Token Index: 891

Text #12

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5456. Min Act: -0.0001

Data Index: 791576 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5288. Min Act: -0.0001

Data Index: 824168 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5271. Min Act: -0.0001

Data Index: 1077481 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1275186 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5057. Min Act: -0.0001

Data Index: 138408 (C4 (Web Text))

Max Activating Token Index: 129

Text #17

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.4853. Min Act: -0.0002

Data Index: 912332 (C4 (Web Text))

Max Activating Token Index: 768

Text #18

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5132. Min Act: -0.0001

Data Index: 11643 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 0.6447. Min Range: -0.6447

Max Act: 0.5161. Min Act: -0.0001

Data Index: 553660 (C4 (Web Text))

Max Activating Token Index: 216