Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3873 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.6669. Min Range: -4.6669

Max Act: 4.6669. Min Act: -0.0000

Data Index: 480857 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 4.6669. Min Range: -4.6669

Max Act: 4.2282. Min Act: -0.0000

Data Index: 1123482 (C4 (Web Text))

Max Activating Token Index: 92

Text #2

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.3557. Min Act: -0.0000

Data Index: 967129 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.1757. Min Act: -0.0000

Data Index: 939314 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.3172. Min Act: -0.0000

Data Index: 735382 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.4284. Min Act: -0.0000

Data Index: 360367 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.3580. Min Act: -0.0000

Data Index: 194790 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.2851. Min Act: -0.0000

Data Index: 1333758 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.2872. Min Act: -0.0000

Data Index: 452859 (C4 (Web Text))

Max Activating Token Index: 519

Text #9

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.0241. Min Act: -0.0000

Data Index: 385623 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 4.6669. Min Range: -4.6669

Max Act: 3.0874. Min Act: -0.0000

Data Index: 394250 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.7269. Min Act: -0.0000

Data Index: 928515 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.5216. Min Act: -0.0000

Data Index: 841097 (C4 (Web Text))

Max Activating Token Index: 247

Text #13

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.7603. Min Act: -0.0000

Data Index: 1150886 (C4 (Web Text))

Max Activating Token Index: 992

Text #14

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.6148. Min Act: -0.0000

Data Index: 546841 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.8926. Min Act: -0.0000

Data Index: 622805 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.5924. Min Act: -0.0000

Data Index: 493217 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.7021. Min Act: -0.0000

Data Index: 239126 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.7047. Min Act: -0.0000

Data Index: 746244 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 4.6669. Min Range: -4.6669

Max Act: 2.5606. Min Act: -0.0000

Data Index: 1054192 (C4 (Web Text))

Max Activating Token Index: 119