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

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

Neuron 3678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0825. Min Range: -2.0825

Max Act: 2.0825. Min Act: -0.0000

Data Index: 285607 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.9268. Min Act: -0.0000

Data Index: 979483 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 2.0825. Min Range: -2.0825

Max Act: 2.0523. Min Act: -0.0000

Data Index: 59722 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.8797. Min Act: -0.0000

Data Index: 1334606 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6658. Min Act: -0.0000

Data Index: 90268 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.7352. Min Act: -0.0000

Data Index: 1311706 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.6828. Min Act: -0.0000

Data Index: 1326337 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.5655. Min Act: -0.0000

Data Index: 640070 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4463. Min Act: -0.0000

Data Index: 405289 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4894. Min Act: -0.0000

Data Index: 530878 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4034. Min Act: -0.0000

Data Index: 661507 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1094248 (C4 (Web Text))

Max Activating Token Index: 32

Text #12

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4792. Min Act: -0.0000

Data Index: 308602 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.3693. Min Act: -0.0000

Data Index: 1531 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.3856. Min Act: -0.0000

Data Index: 1302041 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.4221. Min Act: -0.0000

Data Index: 628358 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.2376. Min Act: -0.0000

Data Index: 834275 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.3802. Min Act: -0.0000

Data Index: 237548 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.2378. Min Act: -0.0000

Data Index: 138063 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 2.0825. Min Range: -2.0825

Max Act: 1.2829. Min Act: -0.0000

Data Index: 116207 (C4 (Web Text))

Max Activating Token Index: 263