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

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

Neuron 2229 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.4399. Min Act: -0.0000

Data Index: 668088 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.5730. Min Act: -0.0001

Data Index: 212047 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.3921. Min Act: -0.0001

Data Index: 922381 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.3750. Min Act: -0.0001

Data Index: 163124 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.2847. Min Act: -0.0000

Data Index: 503564 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.2704. Min Act: -0.0000

Data Index: 479093 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.1752. Min Act: -0.0001

Data Index: 1068499 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.2040. Min Act: -0.0000

Data Index: 1344435 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.1569. Min Act: -0.0001

Data Index: 1226021 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0503. Min Act: -0.0000

Data Index: 56348 (C4 (Web Text))

Max Activating Token Index: 239

Text #10

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0805. Min Act: -0.0000

Data Index: 1262647 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0733. Min Act: -0.0000

Data Index: 779907 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1212315 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 1.5730. Min Range: -1.5730

Max Act: 0.9958. Min Act: -0.0001

Data Index: 31651 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0398. Min Act: -0.0000

Data Index: 73779 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0775. Min Act: -0.0001

Data Index: 57512 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0042. Min Act: -0.0000

Data Index: 395122 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0894. Min Act: -0.0001

Data Index: 504986 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0291. Min Act: -0.0001

Data Index: 1049302 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 1.5730. Min Range: -1.5730

Max Act: 1.0447. Min Act: -0.0000

Data Index: 620721 (C4 (Web Text))

Max Activating Token Index: 974