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

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

Neuron 3442 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0002

Data Index: 287240 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0415. Min Act: -0.0002

Data Index: 1108807 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1236446 (C4 (Web Text))

Max Activating Token Index: 735

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0383. Min Act: -0.0002

Data Index: 1285824 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0378. Min Act: -0.0002

Data Index: 660838 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0391. Min Act: -0.0002

Data Index: 241416 (C4 (Web Text))

Max Activating Token Index: 7

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0387. Min Act: -0.0002

Data Index: 1232695 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1262422 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0374. Min Act: -0.0002

Data Index: 761604 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0368. Min Act: -0.0002

Data Index: 1083775 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0358. Min Act: -0.0002

Data Index: 495552 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0366. Min Act: -0.0002

Data Index: 1043392 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0354. Min Act: -0.0002

Data Index: 1089692 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1311704 (C4 (Web Text))

Max Activating Token Index: 759

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0359. Min Act: -0.0002

Data Index: 720406 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0358. Min Act: -0.0002

Data Index: 67261 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1013167 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0340. Min Act: -0.0002

Data Index: 819564 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0339. Min Act: -0.0002

Data Index: 551211 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0335. Min Act: -0.0002

Data Index: 868772 (C4 (Web Text))

Max Activating Token Index: 857