Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 839 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1758. Min Range: -4.1758

Max Act: 4.1758. Min Act: -0.0000

Data Index: 63575 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 4.1758. Min Range: -4.1758

Max Act: 3.8129. Min Act: -0.0000

Data Index: 205862 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 4.1758. Min Range: -4.1758

Max Act: 3.7144. Min Act: -0.0000

Data Index: 945003 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.9801. Min Act: -0.0000

Data Index: 673522 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.9921. Min Act: -0.0000

Data Index: 397947 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.8232. Min Act: -0.0000

Data Index: 769041 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.6622. Min Act: -0.0000

Data Index: 1168147 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.3100. Min Act: -0.0000

Data Index: 968970 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.1000. Min Act: -0.0000

Data Index: 745502 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.2712. Min Act: -0.0000

Data Index: 374782 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.5165. Min Act: -0.0000

Data Index: 410368 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.2226. Min Act: -0.0000

Data Index: 493402 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.2225. Min Act: -0.0000

Data Index: 470080 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.2004. Min Act: -0.0000

Data Index: 309447 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.3336. Min Act: -0.0000

Data Index: 454814 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.2114. Min Act: -0.0000

Data Index: 202830 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.1862. Min Act: -0.0000

Data Index: 427354 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.0783. Min Act: -0.0000

Data Index: 342040 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.1961. Min Act: -0.0000

Data Index: 305246 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 4.1758. Min Range: -4.1758

Max Act: 2.2984. Min Act: -0.0000

Data Index: 293341 (C4 (Web Text))

Max Activating Token Index: 740