Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1163 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.7270. Min Range: -5.7270

Max Act: 5.7270. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 734

Text #1

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.7759. Min Act: -0.0000

Data Index: 1583232 (Python Code)

Max Activating Token Index: 775

Text #2

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.8535. Min Act: -0.0000

Data Index: 264657 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 5.7270. Min Range: -5.7270

Max Act: 5.0179. Min Act: -0.0000

Data Index: 1364014 (Python Code)

Max Activating Token Index: 406

Text #4

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.5889. Min Act: -0.0000

Data Index: 906244 (C4 (Web Text))

Max Activating Token Index: 185

Text #5

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.9182. Min Act: -0.0000

Data Index: 1655790 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.9595. Min Act: -0.0000

Data Index: 1385132 (Python Code)

Max Activating Token Index: 308

Text #7

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.8516. Min Act: -0.0000

Data Index: 1548218 (Python Code)

Max Activating Token Index: 129

Text #8

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.3548. Min Act: -0.0000

Data Index: 1507841 (Python Code)

Max Activating Token Index: 276

Text #9

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.1780. Min Act: -0.0000

Data Index: 1175550 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.6087. Min Act: -0.0000

Data Index: 1634110 (Python Code)

Max Activating Token Index: 86

Text #11

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.2051. Min Act: -0.0000

Data Index: 487463 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.3510. Min Act: -0.0000

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.5210. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 486

Text #14

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.6858. Min Act: -0.0000

Data Index: 1524707 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.2577. Min Act: -0.0000

Data Index: 1590702 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.6065. Min Act: -0.0000

Data Index: 226177 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.0523. Min Act: -0.0000

Data Index: 727815 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.0032. Min Act: -0.0000

Data Index: 1102387 (C4 (Web Text))

Max Activating Token Index: 564

Text #19

Max Range: 5.7270. Min Range: -5.7270

Max Act: 4.0392. Min Act: -0.0000

Data Index: 179506 (C4 (Web Text))

Max Activating Token Index: 149