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

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

Neuron 4260 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5650. Min Range: -3.5650

Max Act: 3.5650. Min Act: -0.0000

Data Index: 500890 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 3.5650. Min Range: -3.5650

Max Act: 3.4164. Min Act: -0.0000

Data Index: 691759 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.5650. Min Range: -3.5650

Max Act: 3.1875. Min Act: -0.0000

Data Index: 1286719 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 3.5650. Min Range: -3.5650

Max Act: 3.1572. Min Act: -0.0000

Data Index: 819905 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.9725. Min Act: -0.0000

Data Index: 495147 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.9194. Min Act: -0.0000

Data Index: 647031 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.8835. Min Act: -0.0000

Data Index: 729081 (C4 (Web Text))

Max Activating Token Index: 749

Text #7

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.9361. Min Act: -0.0000

Data Index: 757932 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.7238. Min Act: -0.0000

Data Index: 723447 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.3435. Min Act: -0.0000

Data Index: 102869 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.5908. Min Act: -0.0000

Data Index: 835467 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.6596. Min Act: -0.0000

Data Index: 1056733 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.5189. Min Act: -0.0000

Data Index: 951350 (C4 (Web Text))

Max Activating Token Index: 615

Text #13

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.4854. Min Act: -0.0000

Data Index: 702799 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.4746. Min Act: -0.0000

Data Index: 149830 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.4489. Min Act: -0.0000

Data Index: 649605 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.3165. Min Act: -0.0000

Data Index: 384661 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.4642. Min Act: -0.0000

Data Index: 690621 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.2760. Min Act: -0.0000

Data Index: 968775 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 3.5650. Min Range: -3.5650

Max Act: 2.3753. Min Act: -0.0000

Data Index: 977258 (C4 (Web Text))

Max Activating Token Index: 52