Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3780 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.3563. Min Act: -0.0002

Data Index: 278406 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.3863. Min Act: -0.0002

Data Index: 433811 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.5308. Min Act: -0.0001

Data Index: 1241859 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.4724. Min Act: -0.0002

Data Index: 969242 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.3703. Min Act: -0.0002

Data Index: 789056 (C4 (Web Text))

Max Activating Token Index: 974

Text #5

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.2985. Min Act: -0.0002

Data Index: 79121 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.0233. Min Act: -0.0002

Data Index: 318756 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.2728. Min Act: -0.0002

Data Index: 216786 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1551. Min Act: -0.0002

Data Index: 348473 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.0874. Min Act: -0.0002

Data Index: 1200914 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.2159. Min Act: -0.0002

Data Index: 227058 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1998. Min Act: -0.0002

Data Index: 53845 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1198. Min Act: -0.0002

Data Index: 347713 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1959. Min Act: -0.0002

Data Index: 867774 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1705. Min Act: -0.0001

Data Index: 247356 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.2730. Min Act: -0.0001

Data Index: 1328917 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.0636. Min Act: -0.0002

Data Index: 830732 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.0216. Min Act: -0.0002

Data Index: 1241196 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1289. Min Act: -0.0002

Data Index: 489733 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.5308. Min Range: -1.5308

Max Act: 1.1254. Min Act: -0.0001

Data Index: 1232926 (C4 (Web Text))

Max Activating Token Index: 678