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

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

Neuron 3636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1310802 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1338384 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0405. Min Act: -0.0001

Data Index: 521357 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0415. Min Act: -0.0002

Data Index: 567585 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1171471 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0382. Min Act: -0.0002

Data Index: 119899 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0364. Min Act: -0.0002

Data Index: 299591 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0344. Min Act: -0.0001

Data Index: 800023 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0371. Min Act: -0.0001

Data Index: 1131418 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0381. Min Act: -0.0002

Data Index: 167710 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0336. Min Act: -0.0001

Data Index: 1129870 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0363. Min Act: -0.0002

Data Index: 1119494 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0345. Min Act: -0.0002

Data Index: 675109 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1279349 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0348. Min Act: -0.0001

Data Index: 946867 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0368. Min Act: -0.0002

Data Index: 934392 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0368. Min Act: -0.0002

Data Index: 8033 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0334. Min Act: -0.0001

Data Index: 562522 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0340. Min Act: -0.0002

Data Index: 1063279 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1419189 (Python Code)

Max Activating Token Index: 19