Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 899 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.9713. Min Act: -0.0001

Data Index: 1321003 (C4 (Web Text))

Max Activating Token Index: 706

Text #1

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.4265. Min Act: -0.0001

Data Index: 316198 (C4 (Web Text))

Max Activating Token Index: 530

Text #2

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.4706. Min Act: -0.0001

Data Index: 1066890 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.4504. Min Act: -0.0000

Data Index: 189947 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.4320. Min Act: -0.0000

Data Index: 558051 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.3826. Min Act: -0.0000

Data Index: 723720 (C4 (Web Text))

Max Activating Token Index: 325

Text #6

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.3656. Min Act: -0.0001

Data Index: 68780 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.3423. Min Act: -0.0000

Data Index: 834028 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.2852. Min Act: -0.0000

Data Index: 555247 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1590. Min Act: -0.0001

Data Index: 755532 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1993. Min Act: -0.0001

Data Index: 391988 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1724. Min Act: -0.0001

Data Index: 540353 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1118422 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1445. Min Act: -0.0001

Data Index: 92376 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1148. Min Act: -0.0001

Data Index: 456264 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.1013. Min Act: -0.0001

Data Index: 1116908 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.0415. Min Act: -0.0001

Data Index: 119196 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.0701. Min Act: -0.0000

Data Index: 478766 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.0318. Min Act: -0.0001

Data Index: 1005176 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 1.9713. Min Range: -1.9713

Max Act: 1.0176. Min Act: -0.0000

Data Index: 240287 (C4 (Web Text))

Max Activating Token Index: 969