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

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

Neuron 2383 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6857. Min Act: -0.0000

Data Index: 1512258 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1376906 (Python Code)

Max Activating Token Index: 923

Text #2

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.7323. Min Act: -0.0000

Data Index: 1095900 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6871. Min Act: -0.0000

Data Index: 918128 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6602. Min Act: -0.0000

Data Index: 313227 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6637. Min Act: -0.0000

Data Index: 275461 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6632. Min Act: -0.0000

Data Index: 375391 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1197581 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6378. Min Act: -0.0000

Data Index: 638276 (C4 (Web Text))

Max Activating Token Index: 464

Text #9

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1199020 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6534. Min Act: -0.0000

Data Index: 439831 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1609332 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6437. Min Act: -0.0000

Data Index: 883501 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6600. Min Act: -0.0000

Data Index: 917717 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6385. Min Act: -0.0000

Data Index: 586951 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6637. Min Act: -0.0000

Data Index: 1235556 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6704. Min Act: -0.0000

Data Index: 557031 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6250. Min Act: -0.0000

Data Index: 96311 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6099. Min Act: -0.0000

Data Index: 1038763 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6077. Min Act: -0.0000

Data Index: 189305 (C4 (Web Text))

Max Activating Token Index: 466