Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.8889. Min Act: -0.0001

Data Index: 871121 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6797. Min Act: -0.0001

Data Index: 171469 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.7022. Min Act: -0.0001

Data Index: 1196976 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6570. Min Act: -0.0001

Data Index: 43435 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6347. Min Act: -0.0001

Data Index: 461303 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.5854. Min Act: -0.0001

Data Index: 84297 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1278496 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6592. Min Act: -0.0001

Data Index: 180436 (C4 (Web Text))

Max Activating Token Index: 36

Text #8

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6525. Min Act: -0.0001

Data Index: 1163882 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6394. Min Act: -0.0001

Data Index: 801447 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6469. Min Act: -0.0001

Data Index: 173846 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6412. Min Act: -0.0001

Data Index: 1179201 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6581. Min Act: -0.0001

Data Index: 526085 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6313. Min Act: -0.0001

Data Index: 578996 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6268. Min Act: -0.0001

Data Index: 287906 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6249. Min Act: -0.0001

Data Index: 674539 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6376. Min Act: -0.0001

Data Index: 577784 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6223. Min Act: -0.0001

Data Index: 561934 (C4 (Web Text))

Max Activating Token Index: 171

Text #18

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6209. Min Act: -0.0001

Data Index: 799428 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.8889. Min Range: -0.8889

Max Act: 0.6151. Min Act: -0.0001

Data Index: 114625 (C4 (Web Text))

Max Activating Token Index: 143