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

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

Neuron 3973 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1257. Min Act: -0.0000

Data Index: 366784 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.0855. Min Act: -0.0000

Data Index: 677825 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.2223. Min Act: -0.0000

Data Index: 1312822 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1010. Min Act: -0.0000

Data Index: 547411 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1306 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.0555. Min Act: -0.0000

Data Index: 338687 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1000392 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.0458. Min Act: -0.0000

Data Index: 451382 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.0351. Min Act: -0.0000

Data Index: 867184 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 1.2223. Min Range: -1.2223

Max Act: 1.0394. Min Act: -0.0000

Data Index: 695163 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9287. Min Act: -0.0000

Data Index: 602365 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9895. Min Act: -0.0000

Data Index: 301057 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9510. Min Act: -0.0000

Data Index: 254525 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1082446 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1217905 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1058729 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.8715. Min Act: -0.0000

Data Index: 799072 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1163104 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.8946. Min Act: -0.0000

Data Index: 1091818 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.2223. Min Range: -1.2223

Max Act: 0.9506. Min Act: -0.0000

Data Index: 200735 (C4 (Web Text))

Max Activating Token Index: 859