Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2387 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.1161. Min Range: -2.1161

Max Act: 2.1161. Min Act: -0.0000

Data Index: 226858 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 2.1161. Min Range: -2.1161

Max Act: 2.1101. Min Act: -0.0000

Data Index: 255224 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.9699. Min Act: -0.0000

Data Index: 351542 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.6927. Min Act: -0.0000

Data Index: 621054 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.5627. Min Act: -0.0001

Data Index: 1034450 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.8797. Min Act: -0.0000

Data Index: 33250 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.4018. Min Act: -0.0000

Data Index: 921926 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.3788. Min Act: -0.0000

Data Index: 287397 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.4106. Min Act: -0.0000

Data Index: 52144 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.3354. Min Act: -0.0000

Data Index: 349113 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.3357. Min Act: -0.0001

Data Index: 1634642 (Python Code)

Max Activating Token Index: 915

Text #11

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.4354. Min Act: -0.0001

Data Index: 562972 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.3415. Min Act: -0.0000

Data Index: 710186 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.2494. Min Act: -0.0001

Data Index: 1603244 (Python Code)

Max Activating Token Index: 795

Text #14

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.2817. Min Act: -0.0000

Data Index: 386770 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.2718. Min Act: -0.0001

Data Index: 589407 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.3289. Min Act: -0.0001

Data Index: 472532 (C4 (Web Text))

Max Activating Token Index: 735

Text #17

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.2543. Min Act: -0.0000

Data Index: 370314 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.2659. Min Act: -0.0001

Data Index: 5454 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 2.1161. Min Range: -2.1161

Max Act: 1.2592. Min Act: -0.0000

Data Index: 296891 (C4 (Web Text))

Max Activating Token Index: 1023