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

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

Neuron 1984 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.5796. Min Act: -0.0000

Data Index: 1204629 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.7378. Min Act: -0.0000

Data Index: 905675 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.1603. Min Act: -0.0000

Data Index: 801209 (C4 (Web Text))

Max Activating Token Index: 339

Text #3

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.0348. Min Act: -0.0000

Data Index: 98404 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.0450. Min Act: -0.0000

Data Index: 1088522 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.0354. Min Act: 0.0000

Data Index: 443783 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.0825. Min Act: -0.0000

Data Index: 379214 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9902. Min Act: -0.0000

Data Index: 1100466 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 1.7378. Min Range: -1.7378

Max Act: 1.0437. Min Act: 0.0000

Data Index: 1210946 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9452. Min Act: -0.0000

Data Index: 627129 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9481. Min Act: -0.0000

Data Index: 51271 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9226. Min Act: -0.0000

Data Index: 95080 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9430. Min Act: -0.0000

Data Index: 886156 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9028. Min Act: -0.0000

Data Index: 255172 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9044. Min Act: -0.0000

Data Index: 826268 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.9523. Min Act: -0.0000

Data Index: 1033639 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.8552. Min Act: -0.0000

Data Index: 502530 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.8528. Min Act: 0.0001

Data Index: 486161 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.8384. Min Act: -0.0000

Data Index: 326959 (C4 (Web Text))

Max Activating Token Index: 475

Text #19

Max Range: 1.7378. Min Range: -1.7378

Max Act: 0.8549. Min Act: 0.0000

Data Index: 1026148 (C4 (Web Text))

Max Activating Token Index: 665