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

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

Neuron 3733 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7896. Min Act: -0.0000

Data Index: 1362701 (Python Code)

Max Activating Token Index: 476

Text #1

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7353. Min Act: -0.0000

Data Index: 634026 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1629215 (Python Code)

Max Activating Token Index: 31

Text #3

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6834. Min Act: -0.0000

Data Index: 94421 (C4 (Web Text))

Max Activating Token Index: 946

Text #4

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6634. Min Act: -0.0000

Data Index: 731814 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6802. Min Act: -0.0000

Data Index: 72388 (C4 (Web Text))

Max Activating Token Index: 575

Text #6

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6611. Min Act: -0.0000

Data Index: 713048 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6055. Min Act: -0.0000

Data Index: 458253 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6231. Min Act: -0.0000

Data Index: 435312 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1501460 (Python Code)

Max Activating Token Index: 20

Text #10

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6084. Min Act: -0.0000

Data Index: 266984 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6158. Min Act: -0.0000

Data Index: 1632811 (Python Code)

Max Activating Token Index: 424

Text #12

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1023790 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5922. Min Act: -0.0000

Data Index: 625971 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1351654 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.6060. Min Act: -0.0000

Data Index: 645968 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5928. Min Act: -0.0000

Data Index: 659324 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5660. Min Act: -0.0000

Data Index: 96298 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5339. Min Act: -0.0000

Data Index: 514104 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.7896. Min Range: -0.7896

Max Act: 0.5149. Min Act: -0.0000

Data Index: 963547 (C4 (Web Text))

Max Activating Token Index: 627