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

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

Neuron 5944 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0000

Data Index: 311543 (C4 (Web Text))

Max Activating Token Index: 21

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2656. Min Act: -0.0000

Data Index: 1277180 (C4 (Web Text))

Max Activating Token Index: 965

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2372. Min Act: -0.0000

Data Index: 356249 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1280883 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2152. Min Act: -0.0000

Data Index: 1357132 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1325767 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2035. Min Act: -0.0000

Data Index: 804681 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2001. Min Act: -0.0000

Data Index: 955937 (C4 (Web Text))

Max Activating Token Index: 254

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1988. Min Act: -0.0000

Data Index: 113361 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1237949 (C4 (Web Text))

Max Activating Token Index: 515

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1964. Min Act: -0.0000

Data Index: 518988 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2056. Min Act: -0.0000

Data Index: 979471 (C4 (Web Text))

Max Activating Token Index: 699

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1919. Min Act: -0.0000

Data Index: 675493 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1066738 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1331082 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2065. Min Act: -0.0000

Data Index: 783235 (C4 (Web Text))

Max Activating Token Index: 276

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1010701 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2040. Min Act: -0.0000

Data Index: 936794 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1024670 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1854. Min Act: -0.0000

Data Index: 612553 (C4 (Web Text))

Max Activating Token Index: 663