Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1965 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0549. Min Act: -0.0003

Data Index: 971162 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0398. Min Act: -0.0003

Data Index: 306812 (C4 (Web Text))

Max Activating Token Index: 1006

Text #2

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0401. Min Act: -0.0003

Data Index: 686729 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0382. Min Act: -0.0003

Data Index: 772530 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0371. Min Act: -0.0003

Data Index: 814280 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1071930 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1077046 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0363. Min Act: -0.0003

Data Index: 77736 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0366. Min Act: -0.0004

Data Index: 957749 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0350. Min Act: -0.0003

Data Index: 718370 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0362. Min Act: -0.0003

Data Index: 49904 (C4 (Web Text))

Max Activating Token Index: 175

Text #11

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0360. Min Act: -0.0003

Data Index: 1051510 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0351. Min Act: -0.0003

Data Index: 70642 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0345. Min Act: -0.0003

Data Index: 667656 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1330426 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0357. Min Act: -0.0003

Data Index: 413142 (C4 (Web Text))

Max Activating Token Index: 589

Text #16

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0337. Min Act: -0.0003

Data Index: 1035081 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0346. Min Act: -0.0003

Data Index: 653597 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0336. Min Act: -0.0003

Data Index: 968703 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0549. Min Range: -0.0549

Max Act: 0.0339. Min Act: -0.0003

Data Index: 737500 (C4 (Web Text))

Max Activating Token Index: 913