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

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

Neuron 4254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.4341. Min Act: -0.0000

Data Index: 1252469 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1444334 (Python Code)

Max Activating Token Index: 187

Text #2

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1632916 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.3089. Min Act: -0.0000

Data Index: 769898 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2446. Min Act: -0.0000

Data Index: 7730 (C4 (Web Text))

Max Activating Token Index: 737

Text #5

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1851. Min Act: -0.0000

Data Index: 340190 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2822. Min Act: -0.0000

Data Index: 1442322 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1791. Min Act: -0.0000

Data Index: 1648477 (Python Code)

Max Activating Token Index: 234

Text #8

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1615363 (Python Code)

Max Activating Token Index: 594

Text #9

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1230286 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2369. Min Act: -0.0000

Data Index: 1421977 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1938. Min Act: -0.0000

Data Index: 1475908 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1727. Min Act: -0.0000

Data Index: 171139 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.2060. Min Act: -0.0000

Data Index: 738461 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1474. Min Act: -0.0000

Data Index: 1591456 (Python Code)

Max Activating Token Index: 679

Text #15

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1350. Min Act: -0.0000

Data Index: 1384202 (Python Code)

Max Activating Token Index: 397

Text #16

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1264. Min Act: -0.0000

Data Index: 1647163 (Python Code)

Max Activating Token Index: 161

Text #17

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1632458 (Python Code)

Max Activating Token Index: 268

Text #18

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1595349 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 1.4341. Min Range: -1.4341

Max Act: 1.0882. Min Act: -0.0000

Data Index: 251197 (C4 (Web Text))

Max Activating Token Index: 608