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

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

Neuron 3132 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: 0.1420. Min Range: -0.1420

Max Act: 0.1420. Min Act: -0.0000

Data Index: 918889 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1227. Min Act: -0.0001

Data Index: 1505297 (Python Code)

Max Activating Token Index: 898

Text #2

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1295. Min Act: -0.0000

Data Index: 228512 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1050525 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1124. Min Act: -0.0000

Data Index: 1176566 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1125. Min Act: -0.0000

Data Index: 704802 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1029. Min Act: -0.0000

Data Index: 642693 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1090859 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1002. Min Act: -0.0000

Data Index: 765834 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1037. Min Act: -0.0000

Data Index: 670373 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1041. Min Act: -0.0000

Data Index: 525200 (C4 (Web Text))

Max Activating Token Index: 937

Text #11

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0983. Min Act: -0.0000

Data Index: 154382 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1011. Min Act: -0.0000

Data Index: 437191 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1009. Min Act: -0.0000

Data Index: 954287 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1042. Min Act: -0.0000

Data Index: 342145 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1494501 (Python Code)

Max Activating Token Index: 164

Text #16

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1480405 (Python Code)

Max Activating Token Index: 438

Text #17

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1269494 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0955. Min Act: -0.0000

Data Index: 820714 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0988. Min Act: -0.0000

Data Index: 409744 (C4 (Web Text))

Max Activating Token Index: 593