Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 972 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1258647 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0000

Data Index: 664884 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0442. Min Act: -0.0000

Data Index: 369434 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1162486 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1227664 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0387. Min Act: -0.0000

Data Index: 397357 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0348. Min Act: -0.0000

Data Index: 1164677 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0316. Min Act: -0.0000

Data Index: 1320894 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0385. Min Act: -0.0000

Data Index: 1362523 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0398. Min Act: -0.0000

Data Index: 659076 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0345. Min Act: -0.0001

Data Index: 247947 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1416390 (Python Code)

Max Activating Token Index: 998

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0356. Min Act: -0.0000

Data Index: 1074558 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0377. Min Act: -0.0000

Data Index: 572292 (C4 (Web Text))

Max Activating Token Index: 153

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0358. Min Act: -0.0000

Data Index: 897918 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0361. Min Act: -0.0000

Data Index: 248444 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0381. Min Act: -0.0000

Data Index: 1062588 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0335. Min Act: -0.0000

Data Index: 107087 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1149812 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0367. Min Act: -0.0000

Data Index: 254492 (C4 (Web Text))

Max Activating Token Index: 63