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

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

Neuron 3242 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: 1.1731. Min Range: -1.1731

Max Act: 1.0664. Min Act: -0.0001

Data Index: 435831 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1115 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0369. Min Act: -0.0001

Data Index: 223586 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9442. Min Act: -0.0001

Data Index: 62803 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9192. Min Act: -0.0001

Data Index: 123745 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0215. Min Act: -0.0001

Data Index: 1014269 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0243. Min Act: -0.0001

Data Index: 294580 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9116. Min Act: -0.0001

Data Index: 987004 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0877. Min Act: -0.0001

Data Index: 1257819 (C4 (Web Text))

Max Activating Token Index: 388

Text #9

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0005. Min Act: -0.0001

Data Index: 837128 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0565. Min Act: -0.0001

Data Index: 564719 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0331. Min Act: -0.0001

Data Index: 458154 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9525. Min Act: -0.0001

Data Index: 149634 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1036258 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0182. Min Act: -0.0001

Data Index: 1098203 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 1.1731. Min Range: -1.1731

Max Act: 1.0034. Min Act: -0.0001

Data Index: 187285 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9453. Min Act: -0.0001

Data Index: 1237775 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9033. Min Act: -0.0001

Data Index: 974210 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.8990. Min Act: -0.0001

Data Index: 1274173 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 1.1731. Min Range: -1.1731

Max Act: 0.9440. Min Act: -0.0001

Data Index: 646330 (C4 (Web Text))

Max Activating Token Index: 25