Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 460 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0515. Min Act: -0.0003

Data Index: 568038 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0488. Min Act: -0.0003

Data Index: 478445 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0461. Min Act: -0.0003

Data Index: 195054 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0430. Min Act: -0.0003

Data Index: 817774 (C4 (Web Text))

Max Activating Token Index: 686

Text #4

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0423. Min Act: -0.0003

Data Index: 142350 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1236215 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0403. Min Act: -0.0003

Data Index: 1103049 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0339. Min Act: -0.0003

Data Index: 855062 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0400. Min Act: -0.0003

Data Index: 474297 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0352. Min Act: -0.0003

Data Index: 511816 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1208563 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0393. Min Act: -0.0003

Data Index: 878354 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0427. Min Act: -0.0003

Data Index: 1186609 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0418. Min Act: -0.0003

Data Index: 175126 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1158386 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0380. Min Act: -0.0003

Data Index: 1039633 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1219124 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0338. Min Act: -0.0003

Data Index: 588498 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1307874 (C4 (Web Text))

Max Activating Token Index: 21

Text #19

Max Range: 0.0515. Min Range: -0.0515

Max Act: 0.0341. Min Act: -0.0003

Data Index: 1075118 (C4 (Web Text))

Max Activating Token Index: 274