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

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

Neuron 3203 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3019. Min Range: -3.3019

Max Act: 3.3019. Min Act: -0.0000

Data Index: 1300618 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 3.3019. Min Range: -3.3019

Max Act: 3.2655. Min Act: -0.0000

Data Index: 305413 (C4 (Web Text))

Max Activating Token Index: 717

Text #2

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.8125. Min Act: -0.0000

Data Index: 36683 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.6595. Min Act: -0.0000

Data Index: 505869 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.7658. Min Act: -0.0000

Data Index: 1032666 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.2127. Min Act: -0.0000

Data Index: 668282 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.1168. Min Act: -0.0000

Data Index: 56970 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.0941. Min Act: -0.0000

Data Index: 474990 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.0449. Min Act: -0.0000

Data Index: 869287 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.0697. Min Act: -0.0000

Data Index: 288360 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.9484. Min Act: -0.0000

Data Index: 41470 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 3.3019. Min Range: -3.3019

Max Act: 2.1060. Min Act: -0.0000

Data Index: 1342824 (C4 (Web Text))

Max Activating Token Index: 764

Text #12

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.8824. Min Act: -0.0000

Data Index: 217546 (C4 (Web Text))

Max Activating Token Index: 239

Text #13

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.9723. Min Act: -0.0000

Data Index: 700295 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.9754. Min Act: -0.0000

Data Index: 561071 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.8010. Min Act: -0.0000

Data Index: 872679 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.7881. Min Act: -0.0000

Data Index: 1357584 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.8427. Min Act: -0.0000

Data Index: 498097 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.8262. Min Act: -0.0000

Data Index: 66472 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 3.3019. Min Range: -3.3019

Max Act: 1.8301. Min Act: -0.0000

Data Index: 1257865 (C4 (Web Text))

Max Activating Token Index: 459