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

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

Neuron 13 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: 0.2909. Min Range: -0.2909

Max Act: 0.2909. Min Act: -0.0001

Data Index: 1046852 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2359. Min Act: -0.0000

Data Index: 260337 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2349. Min Act: -0.0000

Data Index: 703434 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2137. Min Act: -0.0000

Data Index: 771186 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1123559 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2145. Min Act: -0.0001

Data Index: 851282 (C4 (Web Text))

Max Activating Token Index: 122

Text #6

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2318. Min Act: -0.0000

Data Index: 402793 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2378. Min Act: -0.0000

Data Index: 85832 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1014888 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2149. Min Act: -0.0000

Data Index: 872517 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2130. Min Act: -0.0001

Data Index: 333967 (C4 (Web Text))

Max Activating Token Index: 106

Text #11

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2018. Min Act: -0.0000

Data Index: 365517 (C4 (Web Text))

Max Activating Token Index: 912

Text #12

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2144. Min Act: -0.0000

Data Index: 15574 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1270520 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2025. Min Act: -0.0001

Data Index: 1404397 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1947. Min Act: -0.0000

Data Index: 723984 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2008. Min Act: -0.0001

Data Index: 854392 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.2078. Min Act: -0.0000

Data Index: 873857 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1988. Min Act: -0.0000

Data Index: 429502 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.2909. Min Range: -0.2909

Max Act: 0.1966. Min Act: -0.0001

Data Index: 966041 (C4 (Web Text))

Max Activating Token Index: 205