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

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

Neuron 1194 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6739. Min Act: -0.0000

Data Index: 348414 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5497. Min Act: -0.0000

Data Index: 328907 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1258126 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5871. Min Act: -0.0000

Data Index: 741644 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1305596 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1085155 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5170. Min Act: -0.0000

Data Index: 23911 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5639. Min Act: -0.0000

Data Index: 74550 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5908. Min Act: -0.0000

Data Index: 833160 (C4 (Web Text))

Max Activating Token Index: 984

Text #9

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5461. Min Act: -0.0000

Data Index: 493309 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1304704 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5204. Min Act: -0.0000

Data Index: 241041 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5436. Min Act: -0.0000

Data Index: 456860 (C4 (Web Text))

Max Activating Token Index: 424

Text #13

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5264. Min Act: -0.0000

Data Index: 651495 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5268. Min Act: -0.0000

Data Index: 399568 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1311251 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5076. Min Act: -0.0000

Data Index: 407011 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.4870. Min Act: -0.0000

Data Index: 56899 (C4 (Web Text))

Max Activating Token Index: 975

Text #18

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5062. Min Act: -0.0000

Data Index: 633549 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.6739. Min Range: -0.6739

Max Act: 0.5060. Min Act: -0.0000

Data Index: 683816 (C4 (Web Text))

Max Activating Token Index: 674