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

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

Neuron 2818 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.6763. Min Act: -0.0000

Data Index: 166501 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.6295. Min Act: -0.0000

Data Index: 625259 (C4 (Web Text))

Max Activating Token Index: 569

Text #2

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.7593. Min Act: -0.0000

Data Index: 493300 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.5376. Min Act: -0.0000

Data Index: 500188 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.5311. Min Act: -0.0000

Data Index: 1333409 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.4248. Min Act: -0.0000

Data Index: 458520 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.3635. Min Act: -0.0000

Data Index: 386512 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.2658. Min Act: -0.0000

Data Index: 728166 (C4 (Web Text))

Max Activating Token Index: 853

Text #8

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.4317. Min Act: -0.0000

Data Index: 744846 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.3490. Min Act: -0.0000

Data Index: 788011 (C4 (Web Text))

Max Activating Token Index: 692

Text #10

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.3507. Min Act: -0.0000

Data Index: 1194654 (C4 (Web Text))

Max Activating Token Index: 853

Text #11

Max Range: 6.7593. Min Range: -6.7593

Max Act: 5.9324. Min Act: -0.0000

Data Index: 496866 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 6.7593. Min Range: -6.7593

Max Act: 5.9310. Min Act: -0.0000

Data Index: 893492 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.1140. Min Act: -0.0000

Data Index: 1260026 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.0919. Min Act: -0.0000

Data Index: 1113101 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 6.7593. Min Range: -6.7593

Max Act: 6.2165. Min Act: -0.0000

Data Index: 923849 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 6.7593. Min Range: -6.7593

Max Act: 5.9981. Min Act: -0.0000

Data Index: 1277743 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 6.7593. Min Range: -6.7593

Max Act: 5.9750. Min Act: -0.0000

Data Index: 194893 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 6.7593. Min Range: -6.7593

Max Act: 5.9614. Min Act: -0.0000

Data Index: 282515 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 6.7593. Min Range: -6.7593

Max Act: 5.7545. Min Act: -0.0000

Data Index: 1041055 (C4 (Web Text))

Max Activating Token Index: 990