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

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

Neuron 3424 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: 0.5058. Min Range: -0.5058

Max Act: 0.5058. Min Act: -0.0000

Data Index: 740415 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1192542 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4923. Min Act: -0.0000

Data Index: 660701 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4249. Min Act: -0.0000

Data Index: 112227 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1131424 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1356455 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.4118. Min Act: -0.0000

Data Index: 27474 (C4 (Web Text))

Max Activating Token Index: 324

Text #7

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3885. Min Act: -0.0000

Data Index: 637937 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1296995 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3789. Min Act: -0.0000

Data Index: 211964 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3347. Min Act: -0.0000

Data Index: 84172 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3774. Min Act: -0.0000

Data Index: 136814 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3732. Min Act: -0.0000

Data Index: 606833 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3615. Min Act: -0.0000

Data Index: 491651 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3702. Min Act: -0.0000

Data Index: 196104 (C4 (Web Text))

Max Activating Token Index: 629

Text #15

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1029761 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3415. Min Act: -0.0000

Data Index: 230888 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3847. Min Act: -0.0000

Data Index: 808891 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3395. Min Act: -0.0000

Data Index: 242886 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.5058. Min Range: -0.5058

Max Act: 0.3225. Min Act: -0.0000

Data Index: 640170 (C4 (Web Text))

Max Activating Token Index: 613