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

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

Neuron 3567 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1757. Min Range: -2.1757

Max Act: 2.1757. Min Act: -0.0000

Data Index: 1607732 (Python Code)

Max Activating Token Index: 324

Text #1

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.8917. Min Act: -0.0000

Data Index: 1599606 (Python Code)

Max Activating Token Index: 796

Text #2

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.8817. Min Act: -0.0000

Data Index: 1532808 (Python Code)

Max Activating Token Index: 443

Text #3

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.8197. Min Act: -0.0000

Data Index: 1529578 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.8131. Min Act: -0.0000

Data Index: 1440614 (Python Code)

Max Activating Token Index: 104

Text #5

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.8046. Min Act: -0.0000

Data Index: 851605 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.6807. Min Act: -0.0000

Data Index: 634737 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.6034. Min Act: -0.0000

Data Index: 721585 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.6863. Min Act: -0.0000

Data Index: 295228 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1646694 (Python Code)

Max Activating Token Index: 43

Text #10

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1444876 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1472927 (Python Code)

Max Activating Token Index: 112

Text #12

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.4197. Min Act: -0.0000

Data Index: 592 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.4159. Min Act: -0.0000

Data Index: 1159822 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1466643 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1499670 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1072923 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.3916. Min Act: -0.0000

Data Index: 1298109 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.3158. Min Act: -0.0000

Data Index: 1379180 (Python Code)

Max Activating Token Index: 77

Text #19

Max Range: 2.1757. Min Range: -2.1757

Max Act: 1.2900. Min Act: -0.0000

Data Index: 883089 (C4 (Web Text))

Max Activating Token Index: 528