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

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

Neuron 789 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1502883 (Python Code)

Max Activating Token Index: 479

Text #1

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0388. Min Act: -0.0001

Data Index: 1088698 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1058854 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0357. Min Act: -0.0001

Data Index: 586293 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0360. Min Act: -0.0001

Data Index: 606242 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0332. Min Act: -0.0001

Data Index: 447170 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0348. Min Act: -0.0001

Data Index: 1216160 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0347. Min Act: -0.0001

Data Index: 117968 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0323. Min Act: -0.0001

Data Index: 243877 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0333. Min Act: -0.0001

Data Index: 571319 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0320. Min Act: -0.0001

Data Index: 583078 (C4 (Web Text))

Max Activating Token Index: 126

Text #11

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0309. Min Act: -0.0001

Data Index: 1256871 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0313. Min Act: -0.0001

Data Index: 371447 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1140321 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0338. Min Act: -0.0001

Data Index: 1113028 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0320. Min Act: -0.0001

Data Index: 504415 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0319. Min Act: -0.0001

Data Index: 962681 (C4 (Web Text))

Max Activating Token Index: 98

Text #17

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0336. Min Act: -0.0001

Data Index: 627734 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0341. Min Act: -0.0001

Data Index: 1461740 (Python Code)

Max Activating Token Index: 780

Text #19

Max Range: 0.0415. Min Range: -0.0415

Max Act: 0.0342. Min Act: -0.0001

Data Index: 1020148 (C4 (Web Text))

Max Activating Token Index: 634