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

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

Neuron 1828 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0436. Min Range: -3.0436

Max Act: 3.0436. Min Act: -0.0000

Data Index: 1032114 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 3.0436. Min Range: -3.0436

Max Act: 2.0311. Min Act: -0.0000

Data Index: 751743 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.9344. Min Act: -0.0000

Data Index: 481824 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.9871. Min Act: -0.0000

Data Index: 534493 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.9520. Min Act: -0.0000

Data Index: 854593 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8321. Min Act: -0.0000

Data Index: 1242511 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8910. Min Act: -0.0000

Data Index: 47471 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8560. Min Act: -0.0000

Data Index: 1247860 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8384. Min Act: -0.0000

Data Index: 260898 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8924. Min Act: -0.0000

Data Index: 782709 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1038761 (C4 (Web Text))

Max Activating Token Index: 315

Text #11

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.7690. Min Act: -0.0000

Data Index: 543304 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.6523. Min Act: -0.0000

Data Index: 618205 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8547. Min Act: -0.0000

Data Index: 119095 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1279416 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.7257. Min Act: -0.0000

Data Index: 709175 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.7097. Min Act: -0.0000

Data Index: 852458 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.6907. Min Act: -0.0000

Data Index: 457760 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.6083. Min Act: -0.0000

Data Index: 571213 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 3.0436. Min Range: -3.0436

Max Act: 1.8075. Min Act: -0.0000

Data Index: 1125734 (C4 (Web Text))

Max Activating Token Index: 241