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

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

Neuron 3717 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.5013. Min Act: -0.0000

Data Index: 1380282 (Python Code)

Max Activating Token Index: 423

Text #1

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.1775. Min Act: -0.0000

Data Index: 1376126 (Python Code)

Max Activating Token Index: 1009

Text #2

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0535. Min Act: -0.0000

Data Index: 1591328 (Python Code)

Max Activating Token Index: 662

Text #3

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0456. Min Act: -0.0000

Data Index: 43850 (C4 (Web Text))

Max Activating Token Index: 3

Text #4

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1395474 (Python Code)

Max Activating Token Index: 750

Text #5

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0454. Min Act: -0.0000

Data Index: 1434870 (Python Code)

Max Activating Token Index: 225

Text #6

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1555501 (Python Code)

Max Activating Token Index: 1000

Text #7

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0105. Min Act: 0.0000

Data Index: 1445526 (Python Code)

Max Activating Token Index: 979

Text #8

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0077. Min Act: -0.0000

Data Index: 1409053 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 1.5013. Min Range: -1.5013

Max Act: 0.9847. Min Act: -0.0000

Data Index: 1596206 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0637. Min Act: 0.0000

Data Index: 1422234 (Python Code)

Max Activating Token Index: 323

Text #11

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1642895 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0582. Min Act: -0.0000

Data Index: 1529441 (Python Code)

Max Activating Token Index: 922

Text #13

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0180. Min Act: -0.0000

Data Index: 479208 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 1.5013. Min Range: -1.5013

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1591877 (Python Code)

Max Activating Token Index: 515

Text #15

Max Range: 1.5013. Min Range: -1.5013

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1558284 (Python Code)

Max Activating Token Index: 239

Text #16

Max Range: 1.5013. Min Range: -1.5013

Max Act: 0.9885. Min Act: -0.0000

Data Index: 1520325 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 1.5013. Min Range: -1.5013

Max Act: 0.9462. Min Act: 0.0000

Data Index: 1606616 (Python Code)

Max Activating Token Index: 768

Text #18

Max Range: 1.5013. Min Range: -1.5013

Max Act: 0.9628. Min Act: 0.0000

Data Index: 1602242 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 1.5013. Min Range: -1.5013

Max Act: 0.9314. Min Act: 0.0000

Data Index: 1434122 (Python Code)

Max Activating Token Index: 340