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

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

Neuron 1044 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: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0003

Data Index: 610558 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0342. Min Act: -0.0003

Data Index: 973793 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0327. Min Act: -0.0004

Data Index: 92119 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0312. Min Act: -0.0003

Data Index: 340055 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0301. Min Act: -0.0003

Data Index: 182473 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0287. Min Act: -0.0003

Data Index: 45394 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0294. Min Act: -0.0003

Data Index: 989458 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0295. Min Act: -0.0003

Data Index: 625059 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0293. Min Act: -0.0003

Data Index: 897992 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0286. Min Act: -0.0003

Data Index: 118534 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0296. Min Act: -0.0003

Data Index: 218855 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0285. Min Act: -0.0003

Data Index: 47663 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0313. Min Act: -0.0003

Data Index: 307780 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1324109 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0285. Min Act: -0.0003

Data Index: 794792 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0276. Min Act: -0.0004

Data Index: 672705 (C4 (Web Text))

Max Activating Token Index: 593

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1285529 (C4 (Web Text))

Max Activating Token Index: 29

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0259. Min Act: -0.0003

Data Index: 940300 (C4 (Web Text))

Max Activating Token Index: 553

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0271. Min Act: -0.0004

Data Index: 246832 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1207987 (C4 (Web Text))

Max Activating Token Index: 648