Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2224 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.7563. Min Act: -0.0001

Data Index: 81165 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.8474. Min Act: -0.0002

Data Index: 901407 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6117. Min Act: -0.0002

Data Index: 242728 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6401. Min Act: -0.0002

Data Index: 315356 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5493. Min Act: -0.0001

Data Index: 923979 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6010. Min Act: -0.0001

Data Index: 1350208 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4861. Min Act: -0.0001

Data Index: 630324 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4904. Min Act: -0.0001

Data Index: 1094411 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4609. Min Act: -0.0001

Data Index: 492842 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5324. Min Act: -0.0001

Data Index: 446581 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.3426. Min Act: -0.0001

Data Index: 778776 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.2751. Min Act: -0.0001

Data Index: 410577 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5491. Min Act: -0.0001

Data Index: 722455 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.3461. Min Act: -0.0001

Data Index: 198711 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4234. Min Act: -0.0001

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4192. Min Act: -0.0001

Data Index: 1291209 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4866. Min Act: -0.0001

Data Index: 1185677 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4201. Min Act: -0.0001

Data Index: 616053 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.3333. Min Act: -0.0002

Data Index: 764439 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5154. Min Act: -0.0001

Data Index: 898542 (C4 (Web Text))

Max Activating Token Index: 138