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

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

Neuron 529 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: 0.7549. Min Range: -0.7549

Max Act: 0.6885. Min Act: -0.0000

Data Index: 648662 (C4 (Web Text))

Max Activating Token Index: 650

Text #1

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.7549. Min Act: -0.0000

Data Index: 54989 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.7252. Min Act: -0.0000

Data Index: 282150 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.7290. Min Act: -0.0000

Data Index: 951348 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6511. Min Act: -0.0000

Data Index: 185106 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6778. Min Act: -0.0000

Data Index: 813869 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.7003. Min Act: -0.0000

Data Index: 446523 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6797. Min Act: -0.0000

Data Index: 651907 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6579. Min Act: -0.0000

Data Index: 975028 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.7115. Min Act: -0.0000

Data Index: 958550 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.7342. Min Act: -0.0000

Data Index: 474283 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6887. Min Act: -0.0000

Data Index: 626448 (C4 (Web Text))

Max Activating Token Index: 397

Text #12

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6532. Min Act: -0.0000

Data Index: 576178 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1378579 (Python Code)

Max Activating Token Index: 733

Text #14

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6760. Min Act: -0.0000

Data Index: 499612 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6737. Min Act: -0.0000

Data Index: 750834 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1420204 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6521. Min Act: -0.0000

Data Index: 981675 (C4 (Web Text))

Max Activating Token Index: 622

Text #18

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6560. Min Act: -0.0000

Data Index: 454588 (C4 (Web Text))

Max Activating Token Index: 747

Text #19

Max Range: 0.7549. Min Range: -0.7549

Max Act: 0.6692. Min Act: -0.0000

Data Index: 1144390 (C4 (Web Text))

Max Activating Token Index: 154