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

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

Neuron 4970 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: 0.9458. Min Range: -0.9458

Max Act: 0.9458. Min Act: -0.0000

Data Index: 223006 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7752. Min Act: -0.0000

Data Index: 365179 (C4 (Web Text))

Max Activating Token Index: 570

Text #2

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.7709. Min Act: -0.0000

Data Index: 625333 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.5910. Min Act: -0.0000

Data Index: 991983 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6792. Min Act: -0.0000

Data Index: 898487 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1056467 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6947. Min Act: -0.0000

Data Index: 804097 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6200. Min Act: -0.0000

Data Index: 521861 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6578. Min Act: -0.0000

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.5937. Min Act: -0.0000

Data Index: 885228 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6331. Min Act: -0.0000

Data Index: 625141 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1306137 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6323. Min Act: -0.0000

Data Index: 24416 (C4 (Web Text))

Max Activating Token Index: 416

Text #13

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1042224 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6356. Min Act: -0.0000

Data Index: 319369 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6258. Min Act: -0.0000

Data Index: 357765 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.5756. Min Act: -0.0000

Data Index: 1253926 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.5973. Min Act: -0.0000

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.5910. Min Act: -0.0000

Data Index: 588271 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.9458. Min Range: -0.9458

Max Act: 0.6135. Min Act: -0.0000

Data Index: 622181 (C4 (Web Text))

Max Activating Token Index: 746