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

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

Neuron 837 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.9391. Min Act: -0.0000

Data Index: 117454 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.9391. Min Range: -3.9391

Max Act: 2.8145. Min Act: -0.0000

Data Index: 313678 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 3.9391. Min Range: -3.9391

Max Act: 3.0135. Min Act: -0.0000

Data Index: 31179 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 3.9391. Min Range: -3.9391

Max Act: 2.8596. Min Act: -0.0000

Data Index: 1516731 (Python Code)

Max Activating Token Index: 544

Text #4

Max Range: 3.9391. Min Range: -3.9391

Max Act: 2.2858. Min Act: -0.0000

Data Index: 723271 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 3.9391. Min Range: -3.9391

Max Act: 2.2916. Min Act: -0.0000

Data Index: 1642617 (Python Code)

Max Activating Token Index: 509

Text #6

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.7495. Min Act: -0.0000

Data Index: 182354 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.9381. Min Act: -0.0000

Data Index: 884800 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 3.9391. Min Range: -3.9391

Max Act: 2.0388. Min Act: -0.0000

Data Index: 1541994 (Python Code)

Max Activating Token Index: 418

Text #9

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.8123. Min Act: -0.0000

Data Index: 522377 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.8304. Min Act: -0.0000

Data Index: 886393 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.9177. Min Act: -0.0000

Data Index: 1516467 (Python Code)

Max Activating Token Index: 514

Text #12

Max Range: 3.9391. Min Range: -3.9391

Max Act: 2.3486. Min Act: -0.0000

Data Index: 186696 (C4 (Web Text))

Max Activating Token Index: 811

Text #13

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.9637. Min Act: -0.0000

Data Index: 849794 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.7501. Min Act: -0.0000

Data Index: 452174 (C4 (Web Text))

Max Activating Token Index: 107

Text #15

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.6965. Min Act: -0.0000

Data Index: 428974 (C4 (Web Text))

Max Activating Token Index: 558

Text #16

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.6634. Min Act: -0.0000

Data Index: 1468171 (Python Code)

Max Activating Token Index: 682

Text #17

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.7510. Min Act: -0.0000

Data Index: 1612379 (Python Code)

Max Activating Token Index: 551

Text #18

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.6850. Min Act: -0.0000

Data Index: 135373 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 3.9391. Min Range: -3.9391

Max Act: 1.6724. Min Act: -0.0000

Data Index: 1077627 (C4 (Web Text))

Max Activating Token Index: 479