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

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

Neuron 1166 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.7013. Min Act: -0.0000

Data Index: 1490511 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6260. Min Act: -0.0000

Data Index: 1626022 (Python Code)

Max Activating Token Index: 617

Text #2

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1504508 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1411153 (Python Code)

Max Activating Token Index: 940

Text #4

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5307. Min Act: -0.0000

Data Index: 1468548 (Python Code)

Max Activating Token Index: 710

Text #5

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1643552 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4959. Min Act: -0.0000

Data Index: 1433053 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.5157. Min Act: -0.0000

Data Index: 1617671 (Python Code)

Max Activating Token Index: 770

Text #8

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4951. Min Act: -0.0000

Data Index: 1421827 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1413205 (Python Code)

Max Activating Token Index: 110

Text #10

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4519. Min Act: -0.0000

Data Index: 1610483 (Python Code)

Max Activating Token Index: 911

Text #11

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1538363 (Python Code)

Max Activating Token Index: 226

Text #12

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1499808 (Python Code)

Max Activating Token Index: 757

Text #13

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1500232 (Python Code)

Max Activating Token Index: 841

Text #14

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1475783 (Python Code)

Max Activating Token Index: 651

Text #15

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1506424 (Python Code)

Max Activating Token Index: 751

Text #16

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1444397 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1444335 (Python Code)

Max Activating Token Index: 919

Text #18

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1442377 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 0.7013. Min Range: -0.7013

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1629952 (Python Code)

Max Activating Token Index: 304