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

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

Neuron 488 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2811. Min Act: -0.0001

Data Index: 1179499 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3806. Min Act: -0.0001

Data Index: 803266 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.4014. Min Act: -0.0001

Data Index: 1061381 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3150. Min Act: -0.0001

Data Index: 1385697 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2587. Min Act: -0.0001

Data Index: 870013 (C4 (Web Text))

Max Activating Token Index: 922

Text #5

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.3649. Min Act: -0.0001

Data Index: 261020 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2230. Min Act: -0.0001

Data Index: 1473347 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2134. Min Act: -0.0001

Data Index: 572554 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0685. Min Act: -0.0001

Data Index: 1569391 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1974. Min Act: -0.0001

Data Index: 1026714 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1257. Min Act: -0.0001

Data Index: 1594017 (Python Code)

Max Activating Token Index: 311

Text #11

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1201. Min Act: -0.0001

Data Index: 489324 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2622. Min Act: -0.0001

Data Index: 1644217 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1746. Min Act: -0.0001

Data Index: 476263 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2207. Min Act: -0.0001

Data Index: 241898 (C4 (Web Text))

Max Activating Token Index: 697

Text #15

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1377. Min Act: -0.0001

Data Index: 938626 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.1497. Min Act: -0.0001

Data Index: 1633014 (Python Code)

Max Activating Token Index: 140

Text #17

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.0872. Min Act: -0.0001

Data Index: 674516 (C4 (Web Text))

Max Activating Token Index: 728

Text #18

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2304. Min Act: -0.0001

Data Index: 1568065 (Python Code)

Max Activating Token Index: 512

Text #19

Max Range: 1.4014. Min Range: -1.4014

Max Act: 1.2158. Min Act: -0.0001

Data Index: 1420653 (Python Code)

Max Activating Token Index: 33