Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0404. Min Act: -0.0002

Data Index: 122408 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0399. Min Act: -0.0002

Data Index: 154073 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0413. Min Act: -0.0002

Data Index: 117574 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0444. Min Act: -0.0002

Data Index: 439334 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1058062 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0413. Min Act: -0.0002

Data Index: 360680 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0386. Min Act: -0.0002

Data Index: 552802 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0371. Min Act: -0.0002

Data Index: 1205124 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0385. Min Act: -0.0002

Data Index: 794987 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0382. Min Act: -0.0002

Data Index: 919386 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0357. Min Act: -0.0002

Data Index: 949068 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0377. Min Act: -0.0002

Data Index: 338620 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1124849 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0345. Min Act: -0.0002

Data Index: 829358 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0323. Min Act: -0.0002

Data Index: 183893 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0364. Min Act: -0.0002

Data Index: 698913 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0348. Min Act: -0.0002

Data Index: 939445 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0346. Min Act: -0.0002

Data Index: 700082 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0344. Min Act: -0.0002

Data Index: 420526 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0444. Min Range: -0.0444

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1110969 (C4 (Web Text))

Max Activating Token Index: 507