Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1992 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3723. Min Act: -0.0001

Data Index: 782394 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3536. Min Act: -0.0001

Data Index: 1574425 (Python Code)

Max Activating Token Index: 920

Text #2

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3476. Min Act: -0.0001

Data Index: 370075 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3372. Min Act: -0.0001

Data Index: 1449426 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1378747 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1591697 (Python Code)

Max Activating Token Index: 438

Text #6

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2987. Min Act: -0.0001

Data Index: 467762 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2948. Min Act: -0.0001

Data Index: 1563655 (Python Code)

Max Activating Token Index: 743

Text #8

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3021. Min Act: -0.0001

Data Index: 1382286 (Python Code)

Max Activating Token Index: 74

Text #9

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1452824 (Python Code)

Max Activating Token Index: 208

Text #10

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2892. Min Act: -0.0001

Data Index: 1483912 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3065. Min Act: -0.0001

Data Index: 480845 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2916. Min Act: -0.0001

Data Index: 1552555 (Python Code)

Max Activating Token Index: 765

Text #13

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2870. Min Act: -0.0001

Data Index: 904163 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2828. Min Act: -0.0001

Data Index: 1491362 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2767. Min Act: -0.0001

Data Index: 27259 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.3009. Min Act: -0.0001

Data Index: 599559 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2903. Min Act: -0.0001

Data Index: 1154569 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2858. Min Act: -0.0001

Data Index: 1498256 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 0.3723. Min Range: -0.3723

Max Act: 0.2834. Min Act: -0.0001

Data Index: 1466597 (Python Code)

Max Activating Token Index: 261