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

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

Neuron 216 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1330922 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.7807. Min Act: -0.0000

Data Index: 810693 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.7364. Min Act: 0.0000

Data Index: 438210 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.7317. Min Act: -0.0000

Data Index: 691782 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6911. Min Act: -0.0000

Data Index: 682650 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.7179. Min Act: -0.0000

Data Index: 864418 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.7400. Min Act: -0.0000

Data Index: 904520 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.7155. Min Act: -0.0000

Data Index: 76810 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1285944 (C4 (Web Text))

Max Activating Token Index: 101

Text #9

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6106. Min Act: -0.0000

Data Index: 128736 (C4 (Web Text))

Max Activating Token Index: 760

Text #10

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6398. Min Act: -0.0000

Data Index: 310256 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1301807 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1266333 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6018. Min Act: -0.0000

Data Index: 835294 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6227. Min Act: -0.0000

Data Index: 387094 (C4 (Web Text))

Max Activating Token Index: 248

Text #15

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6246. Min Act: -0.0000

Data Index: 108657 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6239. Min Act: -0.0000

Data Index: 785833 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.6022. Min Act: -0.0000

Data Index: 341041 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5674. Min Act: -0.0000

Data Index: 731587 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 0.8246. Min Range: -0.8246

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1202510 (C4 (Web Text))

Max Activating Token Index: 819