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

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

Neuron 5059 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: 2.7737. Min Range: -2.7737

Max Act: 2.7737. Min Act: -0.0000

Data Index: 1454222 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.4822. Min Act: -0.0000

Data Index: 1646488 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.4197. Min Act: -0.0000

Data Index: 226904 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.3526. Min Act: -0.0000

Data Index: 39748 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.5400. Min Act: -0.0000

Data Index: 1570482 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.2642. Min Act: -0.0000

Data Index: 1457854 (Python Code)

Max Activating Token Index: 346

Text #6

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.2174. Min Act: -0.0000

Data Index: 265082 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.2340. Min Act: -0.0000

Data Index: 985951 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.0963. Min Act: -0.0000

Data Index: 1000767 (C4 (Web Text))

Max Activating Token Index: 499

Text #9

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.0409. Min Act: -0.0000

Data Index: 1068675 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.0016. Min Act: -0.0000

Data Index: 1553865 (Python Code)

Max Activating Token Index: 923

Text #11

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.0357. Min Act: -0.0000

Data Index: 1081849 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 2.7737. Min Range: -2.7737

Max Act: 2.0254. Min Act: -0.0000

Data Index: 1642998 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.9071. Min Act: -0.0000

Data Index: 1527317 (Python Code)

Max Activating Token Index: 199

Text #14

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.9448. Min Act: -0.0000

Data Index: 819147 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1299382 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.9296. Min Act: -0.0000

Data Index: 1610956 (Python Code)

Max Activating Token Index: 925

Text #17

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.8066. Min Act: -0.0000

Data Index: 323289 (C4 (Web Text))

Max Activating Token Index: 969

Text #18

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.9189. Min Act: -0.0000

Data Index: 1312468 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 2.7737. Min Range: -2.7737

Max Act: 1.8010. Min Act: -0.0000

Data Index: 1609143 (Python Code)

Max Activating Token Index: 42