Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 752 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0418. Min Act: -0.0003

Data Index: 43325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0003

Data Index: 1184616 (C4 (Web Text))

Max Activating Token Index: 79

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1218162 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0359. Min Act: -0.0003

Data Index: 1329508 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0379. Min Act: -0.0004

Data Index: 846953 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0340. Min Act: -0.0003

Data Index: 545784 (C4 (Web Text))

Max Activating Token Index: 515

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1349345 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0377. Min Act: -0.0003

Data Index: 833303 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0349. Min Act: -0.0003

Data Index: 241759 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0386. Min Act: -0.0003

Data Index: 933241 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1153396 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0347. Min Act: -0.0003

Data Index: 494569 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0382. Min Act: -0.0003

Data Index: 723890 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0366. Min Act: -0.0003

Data Index: 434648 (C4 (Web Text))

Max Activating Token Index: 224

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0363. Min Act: -0.0003

Data Index: 682960 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0333. Min Act: -0.0003

Data Index: 326301 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0341. Min Act: -0.0003

Data Index: 664190 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0369. Min Act: -0.0003

Data Index: 370804 (C4 (Web Text))

Max Activating Token Index: 545

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0344. Min Act: -0.0003

Data Index: 654154 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0333. Min Act: -0.0003

Data Index: 546994 (C4 (Web Text))

Max Activating Token Index: 641