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

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

Neuron 1519 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.8097. Min Act: -0.0001

Data Index: 53405 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.5974. Min Act: -0.0001

Data Index: 233749 (C4 (Web Text))

Max Activating Token Index: 254

Text #2

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.3642. Min Act: -0.0002

Data Index: 358140 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1190. Min Act: -0.0002

Data Index: 464005 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1058. Min Act: -0.0002

Data Index: 1056801 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.1210. Min Act: -0.0002

Data Index: 158784 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.0691. Min Act: -0.0002

Data Index: 419639 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.0262. Min Act: -0.0002

Data Index: 180717 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9904. Min Act: -0.0002

Data Index: 655201 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.2848. Min Act: -0.0002

Data Index: 868720 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 1.8097. Min Range: -1.8097

Max Act: 1.0669. Min Act: -0.0002

Data Index: 414691 (C4 (Web Text))

Max Activating Token Index: 821

Text #11

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9700. Min Act: -0.0002

Data Index: 892514 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9302. Min Act: -0.0002

Data Index: 224192 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.8393. Min Act: -0.0002

Data Index: 1152154 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9561. Min Act: -0.0002

Data Index: 969704 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9837. Min Act: -0.0002

Data Index: 301238 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9173. Min Act: -0.0002

Data Index: 110807 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9119. Min Act: -0.0002

Data Index: 513856 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.8826. Min Act: -0.0002

Data Index: 98543 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 1.8097. Min Range: -1.8097

Max Act: 0.9912. Min Act: -0.0002

Data Index: 498127 (C4 (Web Text))

Max Activating Token Index: 363