Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3284 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5369. Min Act: -0.0000

Data Index: 1474530 (Python Code)

Max Activating Token Index: 183

Text #2

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4213. Min Act: -0.0000

Data Index: 1644288 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5657. Min Act: -0.0000

Data Index: 309582 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1508558 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5155. Min Act: -0.0000

Data Index: 264860 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1573247 (Python Code)

Max Activating Token Index: 145

Text #7

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1565130 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1080035 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1580778 (Python Code)

Max Activating Token Index: 105

Text #10

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1359408 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4814. Min Act: -0.0000

Data Index: 134348 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4634. Min Act: -0.0000

Data Index: 395729 (C4 (Web Text))

Max Activating Token Index: 368

Text #13

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1221634 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4860. Min Act: -0.0000

Data Index: 1172627 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1604626 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1389789 (Python Code)

Max Activating Token Index: 78

Text #17

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1538369 (Python Code)

Max Activating Token Index: 152

Text #18

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.5137. Min Act: -0.0000

Data Index: 700433 (C4 (Web Text))

Max Activating Token Index: 987

Text #19

Max Range: 0.5863. Min Range: -0.5863

Max Act: 0.4996. Min Act: -0.0000

Data Index: 904560 (C4 (Web Text))

Max Activating Token Index: 676