Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4223 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0423. Min Range: -2.0423

Max Act: 2.0423. Min Act: -0.0000

Data Index: 1148128 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.9949. Min Act: -0.0000

Data Index: 276511 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.6744. Min Act: -0.0000

Data Index: 398510 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1081615 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.6229. Min Act: -0.0000

Data Index: 485587 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.6198. Min Act: -0.0000

Data Index: 645400 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.6075. Min Act: -0.0000

Data Index: 498896 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1271434 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1502519 (Python Code)

Max Activating Token Index: 96

Text #9

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.4423. Min Act: -0.0000

Data Index: 1117168 (C4 (Web Text))

Max Activating Token Index: 636

Text #10

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.5323. Min Act: -0.0000

Data Index: 70402 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.5109. Min Act: -0.0000

Data Index: 234717 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.4192. Min Act: -0.0000

Data Index: 20717 (C4 (Web Text))

Max Activating Token Index: 656

Text #13

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.4154. Min Act: -0.0000

Data Index: 577133 (C4 (Web Text))

Max Activating Token Index: 321

Text #14

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.5512. Min Act: -0.0000

Data Index: 214087 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.4733. Min Act: -0.0000

Data Index: 1049018 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.5615. Min Act: -0.0000

Data Index: 170218 (C4 (Web Text))

Max Activating Token Index: 287

Text #17

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.5491. Min Act: -0.0000

Data Index: 851898 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.5468. Min Act: -0.0000

Data Index: 159078 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 2.0423. Min Range: -2.0423

Max Act: 1.3698. Min Act: -0.0000

Data Index: 667732 (C4 (Web Text))

Max Activating Token Index: 495