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

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

Neuron 4196 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: 1.7140. Min Range: -1.7140

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1068305 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.3158. Min Act: -0.0000

Data Index: 472338 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.2102. Min Act: -0.0000

Data Index: 1187161 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1973. Min Act: -0.0000

Data Index: 791060 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1018. Min Act: -0.0000

Data Index: 821443 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1354. Min Act: -0.0000

Data Index: 591507 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.1026. Min Act: -0.0000

Data Index: 170968 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.0882. Min Act: -0.0000

Data Index: 703259 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 1.7140. Min Range: -1.7140

Max Act: 1.0090. Min Act: -0.0000

Data Index: 1232941 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9852. Min Act: -0.0000

Data Index: 594327 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9184. Min Act: -0.0000

Data Index: 399308 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9699. Min Act: -0.0000

Data Index: 1357604 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.8843. Min Act: -0.0000

Data Index: 964934 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1083696 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9285. Min Act: -0.0000

Data Index: 263937 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1060484 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9297. Min Act: -0.0000

Data Index: 847937 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9179. Min Act: -0.0000

Data Index: 780292 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9213. Min Act: -0.0000

Data Index: 1156405 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 1.7140. Min Range: -1.7140

Max Act: 0.9691. Min Act: -0.0000

Data Index: 828737 (C4 (Web Text))

Max Activating Token Index: 44