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

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

Neuron 2478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2407. Min Act: -0.0001

Data Index: 762294 (C4 (Web Text))

Max Activating Token Index: 902

Text #1

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2412. Min Act: -0.0000

Data Index: 460213 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2280. Min Act: -0.0000

Data Index: 301268 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2176. Min Act: -0.0001

Data Index: 688764 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2076. Min Act: -0.0000

Data Index: 126595 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1324839 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2078. Min Act: -0.0001

Data Index: 47538 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2052. Min Act: -0.0001

Data Index: 61226 (C4 (Web Text))

Max Activating Token Index: 537

Text #8

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1990. Min Act: -0.0001

Data Index: 158924 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1995. Min Act: -0.0001

Data Index: 680054 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1902. Min Act: -0.0001

Data Index: 890232 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1836. Min Act: -0.0001

Data Index: 1013465 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1833. Min Act: -0.0001

Data Index: 670714 (C4 (Web Text))

Max Activating Token Index: 985

Text #13

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1919. Min Act: -0.0001

Data Index: 531703 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1913. Min Act: -0.0000

Data Index: 546756 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1759. Min Act: -0.0001

Data Index: 1018838 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1689. Min Act: -0.0000

Data Index: 329626 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1753. Min Act: -0.0001

Data Index: 192371 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1013596 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1998. Min Act: -0.0001

Data Index: 365958 (C4 (Web Text))

Max Activating Token Index: 484