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

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

Neuron 687 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.6591. Min Act: -0.0000

Data Index: 237795 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.7454. Min Act: -0.0000

Data Index: 488648 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.5336. Min Act: -0.0000

Data Index: 64609 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.5405. Min Act: -0.0000

Data Index: 1358250 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.5206. Min Act: -0.0000

Data Index: 234566 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.5274. Min Act: -0.0000

Data Index: 95047 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1245684 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.3731. Min Act: -0.0000

Data Index: 1554318 (Python Code)

Max Activating Token Index: 599

Text #8

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1235260 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.4328. Min Act: -0.0000

Data Index: 1461470 (Python Code)

Max Activating Token Index: 926

Text #10

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.3441. Min Act: -0.0000

Data Index: 739284 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.2989. Min Act: -0.0000

Data Index: 440156 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.2779. Min Act: -0.0000

Data Index: 1206934 (C4 (Web Text))

Max Activating Token Index: 399

Text #13

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1105342 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.3229. Min Act: -0.0000

Data Index: 47010 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.1608. Min Act: -0.0000

Data Index: 445132 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.1495. Min Act: -0.0000

Data Index: 1136689 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.1531. Min Act: -0.0000

Data Index: 459718 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.1995. Min Act: -0.0000

Data Index: 219640 (C4 (Web Text))

Max Activating Token Index: 448

Text #19

Max Range: 1.7454. Min Range: -1.7454

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1242132 (C4 (Web Text))

Max Activating Token Index: 476