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

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

Neuron 4447 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: 3.2169. Min Range: -3.2169

Max Act: 3.2169. Min Act: -0.0000

Data Index: 1465114 (Python Code)

Max Activating Token Index: 293

Text #1

Max Range: 3.2169. Min Range: -3.2169

Max Act: 3.0736. Min Act: -0.0000

Data Index: 1422731 (Python Code)

Max Activating Token Index: 391

Text #2

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.8858. Min Act: -0.0000

Data Index: 1585472 (Python Code)

Max Activating Token Index: 218

Text #3

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.9914. Min Act: -0.0000

Data Index: 1245719 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.9486. Min Act: -0.0000

Data Index: 445622 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.9340. Min Act: -0.0000

Data Index: 1490806 (Python Code)

Max Activating Token Index: 582

Text #6

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.8433. Min Act: -0.0000

Data Index: 1133920 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.7578. Min Act: -0.0000

Data Index: 1036135 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.8054. Min Act: -0.0000

Data Index: 280200 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.7629. Min Act: -0.0000

Data Index: 68074 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.7524. Min Act: -0.0000

Data Index: 930354 (C4 (Web Text))

Max Activating Token Index: 124

Text #11

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.7063. Min Act: -0.0000

Data Index: 1372153 (Python Code)

Max Activating Token Index: 352

Text #12

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.6682. Min Act: -0.0000

Data Index: 302538 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.6666. Min Act: -0.0000

Data Index: 1207645 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.6472. Min Act: -0.0000

Data Index: 1554291 (Python Code)

Max Activating Token Index: 455

Text #15

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.6339. Min Act: -0.0000

Data Index: 1637260 (Python Code)

Max Activating Token Index: 759

Text #16

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.4602. Min Act: -0.0000

Data Index: 684975 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.5919. Min Act: -0.0000

Data Index: 448930 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.5669. Min Act: -0.0000

Data Index: 1226392 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 3.2169. Min Range: -3.2169

Max Act: 2.6904. Min Act: -0.0000

Data Index: 1134832 (C4 (Web Text))

Max Activating Token Index: 398