Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 718 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0455. Min Act: -0.0003

Data Index: 612647 (C4 (Web Text))

Max Activating Token Index: 206

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0003

Data Index: 66570 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0420. Min Act: -0.0003

Data Index: 535955 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0453. Min Act: -0.0003

Data Index: 156373 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0452. Min Act: -0.0003

Data Index: 1236954 (C4 (Web Text))

Max Activating Token Index: 243

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0426. Min Act: -0.0003

Data Index: 1003788 (C4 (Web Text))

Max Activating Token Index: 5

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0388. Min Act: -0.0003

Data Index: 518431 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0397. Min Act: -0.0003

Data Index: 435866 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0420. Min Act: -0.0003

Data Index: 955656 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1422845 (Python Code)

Max Activating Token Index: 517

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0419. Min Act: -0.0003

Data Index: 1210573 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0380. Min Act: -0.0003

Data Index: 478826 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0399. Min Act: -0.0003

Data Index: 169560 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0429. Min Act: -0.0003

Data Index: 431059 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0412. Min Act: -0.0003

Data Index: 214140 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0400. Min Act: -0.0003

Data Index: 936138 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0396. Min Act: -0.0003

Data Index: 823963 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1056355 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0385. Min Act: -0.0003

Data Index: 4405 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1340358 (C4 (Web Text))

Max Activating Token Index: 376