Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1531 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.8167. Min Act: -0.0006

Data Index: 678114 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7356. Min Act: -0.0006

Data Index: 629253 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7336. Min Act: -0.0006

Data Index: 1228383 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7428. Min Act: -0.0006

Data Index: 440876 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7112. Min Act: -0.0006

Data Index: 1170283 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7675. Min Act: -0.0006

Data Index: 645151 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6739. Min Act: -0.0006

Data Index: 1289354 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7293. Min Act: -0.0006

Data Index: 1114085 (C4 (Web Text))

Max Activating Token Index: 46

Text #8

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6998. Min Act: -0.0006

Data Index: 1178877 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7182. Min Act: -0.0006

Data Index: 1288285 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7132. Min Act: -0.0006

Data Index: 471342 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7129. Min Act: -0.0006

Data Index: 684366 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6913. Min Act: -0.0006

Data Index: 23439 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6928. Min Act: -0.0005

Data Index: 194914 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.7054. Min Act: -0.0006

Data Index: 318712 (C4 (Web Text))

Max Activating Token Index: 459

Text #15

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6731. Min Act: -0.0006

Data Index: 22743 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.5168. Min Act: -0.0006

Data Index: 1086533 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6665. Min Act: -0.0006

Data Index: 46675 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6226. Min Act: -0.0006

Data Index: 1329122 (C4 (Web Text))

Max Activating Token Index: 898

Text #19

Max Range: 0.8167. Min Range: -0.8167

Max Act: 0.6367. Min Act: -0.0006

Data Index: 767994 (C4 (Web Text))

Max Activating Token Index: 861