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

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

Neuron 2406 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1017883 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1194597 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1275119 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4924. Min Act: -0.0000

Data Index: 1654141 (Python Code)

Max Activating Token Index: 226

Text #4

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.5156. Min Act: -0.0000

Data Index: 710449 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1518255 (Python Code)

Max Activating Token Index: 739

Text #6

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1568610 (Python Code)

Max Activating Token Index: 630

Text #7

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4297. Min Act: -0.0000

Data Index: 525999 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1169557 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3932. Min Act: -0.0000

Data Index: 928412 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3991. Min Act: -0.0000

Data Index: 564299 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3896. Min Act: -0.0000

Data Index: 74218 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3824. Min Act: -0.0000

Data Index: 304955 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3686. Min Act: -0.0000

Data Index: 734429 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3810. Min Act: -0.0000

Data Index: 1409857 (Python Code)

Max Activating Token Index: 612

Text #15

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.4178. Min Act: -0.0000

Data Index: 979253 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3841. Min Act: -0.0000

Data Index: 668605 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1579505 (Python Code)

Max Activating Token Index: 478

Text #18

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3736. Min Act: -0.0000

Data Index: 1588436 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 0.5156. Min Range: -0.5156

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1267228 (C4 (Web Text))

Max Activating Token Index: 54