Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3727 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.1785. Min Range: -6.1785

Max Act: 6.1785. Min Act: -0.0000

Data Index: 269714 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 6.1785. Min Range: -6.1785

Max Act: 5.5547. Min Act: -0.0000

Data Index: 856780 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 6.1785. Min Range: -6.1785

Max Act: 4.7519. Min Act: -0.0000

Data Index: 1154643 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 6.1785. Min Range: -6.1785

Max Act: 4.1836. Min Act: -0.0000

Data Index: 873370 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 6.1785. Min Range: -6.1785

Max Act: 4.0419. Min Act: -0.0000

Data Index: 593538 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 6.1785. Min Range: -6.1785

Max Act: 4.1527. Min Act: -0.0000

Data Index: 436295 (C4 (Web Text))

Max Activating Token Index: 141

Text #6

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.9184. Min Act: -0.0000

Data Index: 265332 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 6.1785. Min Range: -6.1785

Max Act: 4.0301. Min Act: -0.0000

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.9533. Min Act: -0.0000

Data Index: 65609 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.7384. Min Act: -0.0000

Data Index: 1302294 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.4690. Min Act: -0.0000

Data Index: 951887 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.6083. Min Act: -0.0000

Data Index: 1059305 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.6767. Min Act: -0.0000

Data Index: 1358656 (C4 (Web Text))

Max Activating Token Index: 298

Text #13

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.5405. Min Act: -0.0000

Data Index: 934778 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.6385. Min Act: -0.0000

Data Index: 408221 (C4 (Web Text))

Max Activating Token Index: 441

Text #15

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.3278. Min Act: -0.0001

Data Index: 740177 (C4 (Web Text))

Max Activating Token Index: 481

Text #16

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.5530. Min Act: -0.0000

Data Index: 1304747 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.3752. Min Act: -0.0000

Data Index: 1189510 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.2959. Min Act: -0.0000

Data Index: 396108 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 6.1785. Min Range: -6.1785

Max Act: 3.3680. Min Act: -0.0001

Data Index: 636041 (C4 (Web Text))

Max Activating Token Index: 51