Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2453 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.6717. Min Act: -0.0003

Data Index: 276718 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.6424. Min Act: -0.0003

Data Index: 751462 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.6380. Min Act: -0.0003

Data Index: 728524 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5572. Min Act: -0.0003

Data Index: 1158004 (C4 (Web Text))

Max Activating Token Index: 310

Text #4

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5971. Min Act: -0.0003

Data Index: 1215872 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5499. Min Act: -0.0003

Data Index: 136670 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5134. Min Act: -0.0003

Data Index: 34539 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5176. Min Act: -0.0003

Data Index: 185233 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5136. Min Act: -0.0003

Data Index: 288265 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5217. Min Act: -0.0003

Data Index: 475915 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5255. Min Act: -0.0003

Data Index: 1067951 (C4 (Web Text))

Max Activating Token Index: 422

Text #11

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5007. Min Act: -0.0003

Data Index: 1013091 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5770. Min Act: -0.0003

Data Index: 306951 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4833. Min Act: -0.0003

Data Index: 275846 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5030. Min Act: -0.0003

Data Index: 852415 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5041. Min Act: -0.0003

Data Index: 624291 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.5179. Min Act: -0.0003

Data Index: 556559 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4497. Min Act: -0.0003

Data Index: 1201180 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4518. Min Act: -0.0003

Data Index: 1142634 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6717. Min Range: -0.6717

Max Act: 0.4663. Min Act: -0.0003

Data Index: 126766 (C4 (Web Text))

Max Activating Token Index: 335