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

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

Neuron 2006 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: 1.1716. Min Range: -1.1716

Max Act: 1.1433. Min Act: -0.0001

Data Index: 627612 (C4 (Web Text))

Max Activating Token Index: 508

Text #1

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.1445. Min Act: -0.0001

Data Index: 1348942 (C4 (Web Text))

Max Activating Token Index: 627

Text #2

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.1498. Min Act: -0.0001

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.1367. Min Act: -0.0001

Data Index: 717734 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0524. Min Act: -0.0001

Data Index: 209837 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0359. Min Act: -0.0001

Data Index: 894352 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.1716. Min Act: -0.0001

Data Index: 56608 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0199. Min Act: -0.0001

Data Index: 29819 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.1260. Min Act: -0.0001

Data Index: 683306 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0039. Min Act: -0.0001

Data Index: 817228 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0516. Min Act: -0.0001

Data Index: 693913 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9636. Min Act: -0.0001

Data Index: 1348016 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0370. Min Act: -0.0001

Data Index: 1099467 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0082. Min Act: -0.0001

Data Index: 186683 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9912. Min Act: -0.0001

Data Index: 292722 (C4 (Web Text))

Max Activating Token Index: 720

Text #15

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9721. Min Act: -0.0001

Data Index: 481738 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0308. Min Act: -0.0001

Data Index: 677302 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9394. Min Act: -0.0001

Data Index: 868336 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 1.1716. Min Range: -1.1716

Max Act: 1.0156. Min Act: -0.0001

Data Index: 2127 (C4 (Web Text))

Max Activating Token Index: 83

Text #19

Max Range: 1.1716. Min Range: -1.1716

Max Act: 0.9813. Min Act: -0.0001

Data Index: 719018 (C4 (Web Text))

Max Activating Token Index: 836