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

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

Neuron 5094 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2125. Min Range: -1.2125

Max Act: 1.2125. Min Act: -0.0001

Data Index: 985648 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.9929. Min Act: -0.0001

Data Index: 1065930 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.2125. Min Range: -1.2125

Max Act: 1.0110. Min Act: -0.0001

Data Index: 1282629 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.9741. Min Act: -0.0001

Data Index: 679421 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.2125. Min Range: -1.2125

Max Act: 1.0413. Min Act: -0.0001

Data Index: 721229 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.9108. Min Act: -0.0001

Data Index: 27387 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8222. Min Act: -0.0001

Data Index: 334746 (C4 (Web Text))

Max Activating Token Index: 705

Text #7

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8452. Min Act: -0.0001

Data Index: 581309 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8335. Min Act: -0.0001

Data Index: 392362 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8236. Min Act: -0.0001

Data Index: 964290 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.9384. Min Act: -0.0001

Data Index: 1303064 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8453. Min Act: -0.0001

Data Index: 254626 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8211. Min Act: -0.0001

Data Index: 1201128 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1323484 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.7862. Min Act: -0.0001

Data Index: 259882 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1008344 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8364. Min Act: -0.0001

Data Index: 1074005 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8741. Min Act: -0.0001

Data Index: 534297 (C4 (Web Text))

Max Activating Token Index: 590

Text #18

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8013. Min Act: -0.0001

Data Index: 403373 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 1.2125. Min Range: -1.2125

Max Act: 0.8437. Min Act: -0.0001

Data Index: 1303059 (C4 (Web Text))

Max Activating Token Index: 514