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

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

Neuron 1999 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2507. Min Act: -0.0001

Data Index: 894053 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2397. Min Act: -0.0001

Data Index: 687710 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2182. Min Act: -0.0002

Data Index: 520069 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2185. Min Act: -0.0001

Data Index: 565485 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2118. Min Act: -0.0002

Data Index: 111776 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2184. Min Act: -0.0002

Data Index: 796469 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1981. Min Act: -0.0001

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2045. Min Act: -0.0001

Data Index: 1137300 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2005. Min Act: -0.0001

Data Index: 1447244 (Python Code)

Max Activating Token Index: 923

Text #9

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2153. Min Act: -0.0002

Data Index: 499530 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2052. Min Act: -0.0002

Data Index: 705820 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2182. Min Act: -0.0002

Data Index: 945936 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1821. Min Act: -0.0001

Data Index: 725995 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2047. Min Act: -0.0001

Data Index: 446244 (C4 (Web Text))

Max Activating Token Index: 38

Text #14

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2038. Min Act: -0.0001

Data Index: 342392 (C4 (Web Text))

Max Activating Token Index: 80

Text #15

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2092. Min Act: -0.0002

Data Index: 1147771 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.2161. Min Act: -0.0002

Data Index: 863050 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1791. Min Act: -0.0002

Data Index: 121433 (C4 (Web Text))

Max Activating Token Index: 325

Text #18

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1990. Min Act: -0.0002

Data Index: 314914 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.2507. Min Range: -0.2507

Max Act: 0.1866. Min Act: -0.0001

Data Index: 101462 (C4 (Web Text))

Max Activating Token Index: 937