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

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

Neuron 2138 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.4710. Min Act: -0.0001

Data Index: 498782 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1551260 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.3091. Min Act: -0.0001

Data Index: 963844 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1022689 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.3268. Min Act: -0.0001

Data Index: 1044298 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.2250. Min Act: -0.0001

Data Index: 1170649 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0390. Min Act: -0.0000

Data Index: 848066 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0695. Min Act: -0.0001

Data Index: 1102418 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.1676. Min Act: -0.0001

Data Index: 528543 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 1.4710. Min Range: -1.4710

Max Act: 0.9996. Min Act: -0.0001

Data Index: 1255412 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0549. Min Act: -0.0001

Data Index: 322309 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1435689 (Python Code)

Max Activating Token Index: 399

Text #12

Max Range: 1.4710. Min Range: -1.4710

Max Act: 0.9434. Min Act: -0.0000

Data Index: 265661 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0149. Min Act: -0.0001

Data Index: 1224023 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0463. Min Act: -0.0001

Data Index: 840710 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0279. Min Act: -0.0001

Data Index: 237012 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0046. Min Act: -0.0001

Data Index: 546698 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 1.4710. Min Range: -1.4710

Max Act: 0.8587. Min Act: -0.0001

Data Index: 1088883 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1106905 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 1.4710. Min Range: -1.4710

Max Act: 1.1204. Min Act: -0.0001

Data Index: 151518 (C4 (Web Text))

Max Activating Token Index: 856