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

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

Neuron 5532 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: 0.8211. Min Range: -0.8211

Max Act: 0.8211. Min Act: -0.0000

Data Index: 975152 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6759. Min Act: -0.0000

Data Index: 795521 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6633. Min Act: -0.0000

Data Index: 429988 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5156. Min Act: -0.0000

Data Index: 707555 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.4237. Min Act: -0.0000

Data Index: 661774 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.4232. Min Act: -0.0000

Data Index: 542644 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2906. Min Act: -0.0000

Data Index: 255451 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1252959 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2634. Min Act: -0.0000

Data Index: 759532 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2634. Min Act: -0.0000

Data Index: 110897 (C4 (Web Text))

Max Activating Token Index: 433

Text #10

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2577. Min Act: -0.0000

Data Index: 760158 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2439. Min Act: -0.0000

Data Index: 221789 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1063453 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2155. Min Act: 0.0000

Data Index: 252878 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2220. Min Act: -0.0000

Data Index: 9416 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2117. Min Act: -0.0000

Data Index: 324944 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2087. Min Act: -0.0000

Data Index: 1007665 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.2066. Min Act: -0.0000

Data Index: 237168 (C4 (Web Text))

Max Activating Token Index: 970

Text #18

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.1993. Min Act: -0.0000

Data Index: 488490 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.1938. Min Act: -0.0000

Data Index: 51815 (C4 (Web Text))

Max Activating Token Index: 600