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

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

Neuron 1824 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.8900. Min Act: -0.0000

Data Index: 652387 (C4 (Web Text))

Max Activating Token Index: 88

Text #1

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.5610. Min Act: -0.0000

Data Index: 652603 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.3483. Min Act: -0.0000

Data Index: 71154 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.3319. Min Act: -0.0000

Data Index: 1292619 (C4 (Web Text))

Max Activating Token Index: 14

Text #4

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.3025. Min Act: -0.0000

Data Index: 608895 (C4 (Web Text))

Max Activating Token Index: 274

Text #5

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.2865. Min Act: -0.0000

Data Index: 258703 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.2413. Min Act: -0.0000

Data Index: 781623 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.2103. Min Act: -0.0000

Data Index: 249877 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.1852. Min Act: -0.0000

Data Index: 699199 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.0821. Min Act: -0.0000

Data Index: 1298521 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.1672. Min Act: -0.0000

Data Index: 900049 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.2734. Min Act: -0.0000

Data Index: 1265940 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.1200. Min Act: -0.0000

Data Index: 576488 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.0716. Min Act: -0.0000

Data Index: 844591 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.0526. Min Act: -0.0000

Data Index: 966281 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.1826. Min Act: -0.0000

Data Index: 1327639 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 2.8900. Min Range: -2.8900

Max Act: 1.9908. Min Act: -0.0000

Data Index: 840451 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.0081. Min Act: -0.0000

Data Index: 1305928 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.8900. Min Range: -2.8900

Max Act: 2.0119. Min Act: -0.0000

Data Index: 799925 (C4 (Web Text))

Max Activating Token Index: 572

Text #19

Max Range: 2.8900. Min Range: -2.8900

Max Act: 1.9710. Min Act: -0.0000

Data Index: 1161278 (C4 (Web Text))

Max Activating Token Index: 726