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

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

Neuron 14 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: 0.9557. Min Range: -0.9557

Max Act: 0.9557. Min Act: -0.0000

Data Index: 408608 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.8271. Min Act: -0.0000

Data Index: 878482 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7773. Min Act: -0.0000

Data Index: 335929 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7141. Min Act: -0.0000

Data Index: 5177 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6929. Min Act: -0.0000

Data Index: 968574 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.7225. Min Act: -0.0000

Data Index: 460777 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1093888 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6726. Min Act: -0.0000

Data Index: 567269 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6725. Min Act: -0.0000

Data Index: 210872 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6168. Min Act: -0.0000

Data Index: 269914 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6199. Min Act: -0.0000

Data Index: 983757 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6126. Min Act: -0.0000

Data Index: 751063 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6065. Min Act: -0.0000

Data Index: 362634 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5764. Min Act: -0.0000

Data Index: 603288 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5876. Min Act: -0.0000

Data Index: 978656 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5449. Min Act: -0.0000

Data Index: 287038 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5885. Min Act: -0.0000

Data Index: 919486 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.6096. Min Act: -0.0000

Data Index: 411939 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1140133 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.9557. Min Range: -0.9557

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1091552 (C4 (Web Text))

Max Activating Token Index: 740