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

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

Neuron 628 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: 2.0524. Min Range: -2.0524

Max Act: 1.9781. Min Act: -0.0000

Data Index: 463654 (C4 (Web Text))

Max Activating Token Index: 243

Text #1

Max Range: 2.0524. Min Range: -2.0524

Max Act: 2.0524. Min Act: -0.0000

Data Index: 651494 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.9707. Min Act: -0.0000

Data Index: 81452 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8019. Min Act: -0.0000

Data Index: 803964 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.8202. Min Act: -0.0000

Data Index: 853397 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.7933. Min Act: -0.0000

Data Index: 198336 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.6982. Min Act: -0.0000

Data Index: 666789 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.6801. Min Act: -0.0000

Data Index: 1165696 (C4 (Web Text))

Max Activating Token Index: 606

Text #8

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5581. Min Act: -0.0000

Data Index: 329189 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.6245. Min Act: -0.0000

Data Index: 497403 (C4 (Web Text))

Max Activating Token Index: 273

Text #10

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.6948. Min Act: -0.0000

Data Index: 206482 (C4 (Web Text))

Max Activating Token Index: 959

Text #11

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.6823. Min Act: -0.0000

Data Index: 844162 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.4465. Min Act: -0.0000

Data Index: 704148 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5202. Min Act: -0.0000

Data Index: 510640 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5273. Min Act: -0.0000

Data Index: 1320311 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5171. Min Act: -0.0000

Data Index: 616749 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5178. Min Act: -0.0000

Data Index: 984055 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5050. Min Act: -0.0000

Data Index: 1049253 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5913. Min Act: -0.0000

Data Index: 515846 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 2.0524. Min Range: -2.0524

Max Act: 1.5043. Min Act: -0.0000

Data Index: 686214 (C4 (Web Text))

Max Activating Token Index: 499