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

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

Neuron 1253 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9828. Min Range: -5.9828

Max Act: 5.9828. Min Act: -0.0000

Data Index: 1563685 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.7228. Min Act: -0.0000

Data Index: 601307 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.5292. Min Act: -0.0000

Data Index: 1627435 (Python Code)

Max Activating Token Index: 846

Text #3

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.5851. Min Act: -0.0000

Data Index: 1467226 (Python Code)

Max Activating Token Index: 544

Text #4

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.3720. Min Act: -0.0000

Data Index: 1511962 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.4010. Min Act: -0.0000

Data Index: 1439510 (Python Code)

Max Activating Token Index: 543

Text #6

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.4865. Min Act: -0.0000

Data Index: 1642996 (Python Code)

Max Activating Token Index: 92

Text #7

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.7317. Min Act: -0.0000

Data Index: 1624224 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.1753. Min Act: -0.0000

Data Index: 1375341 (Python Code)

Max Activating Token Index: 84

Text #9

Max Range: 5.9828. Min Range: -5.9828

Max Act: 3.7830. Min Act: -0.0000

Data Index: 1430943 (Python Code)

Max Activating Token Index: 715

Text #10

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.0980. Min Act: -0.0000

Data Index: 1422766 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.0681. Min Act: -0.0000

Data Index: 1459702 (Python Code)

Max Activating Token Index: 204

Text #12

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.0551. Min Act: -0.0000

Data Index: 807501 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.1069. Min Act: -0.0000

Data Index: 1492349 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 5.9828. Min Range: -5.9828

Max Act: 3.7616. Min Act: -0.0000

Data Index: 1429520 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 5.9828. Min Range: -5.9828

Max Act: 3.7540. Min Act: -0.0000

Data Index: 1508027 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 5.9828. Min Range: -5.9828

Max Act: 4.0731. Min Act: -0.0000

Data Index: 1541296 (Python Code)

Max Activating Token Index: 305

Text #17

Max Range: 5.9828. Min Range: -5.9828

Max Act: 3.5195. Min Act: -0.0000

Data Index: 1589360 (Python Code)

Max Activating Token Index: 471

Text #18

Max Range: 5.9828. Min Range: -5.9828

Max Act: 3.8128. Min Act: -0.0000

Data Index: 1610275 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 5.9828. Min Range: -5.9828

Max Act: 3.5725. Min Act: -0.0000

Data Index: 1398755 (Python Code)

Max Activating Token Index: 260