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

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

Neuron 647 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: 0.2272. Min Range: -0.2272

Max Act: 0.2272. Min Act: -0.0000

Data Index: 390620 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.2261. Min Act: -0.0001

Data Index: 1091131 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1964. Min Act: -0.0001

Data Index: 677518 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1843. Min Act: -0.0001

Data Index: 635941 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1891. Min Act: -0.0001

Data Index: 258852 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1781. Min Act: -0.0000

Data Index: 974575 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1664. Min Act: -0.0000

Data Index: 177810 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1661. Min Act: -0.0000

Data Index: 1258368 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1607. Min Act: -0.0000

Data Index: 1194241 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1650. Min Act: -0.0000

Data Index: 928963 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1284356 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1619. Min Act: -0.0000

Data Index: 955057 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1595. Min Act: -0.0001

Data Index: 29642 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1584. Min Act: -0.0001

Data Index: 435813 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1681. Min Act: -0.0000

Data Index: 773911 (C4 (Web Text))

Max Activating Token Index: 681

Text #15

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1471. Min Act: -0.0000

Data Index: 18663 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1630. Min Act: -0.0000

Data Index: 307146 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1567. Min Act: -0.0000

Data Index: 517429 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1613. Min Act: -0.0000

Data Index: 763150 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.2272. Min Range: -0.2272

Max Act: 0.1504. Min Act: -0.0000

Data Index: 101187 (C4 (Web Text))

Max Activating Token Index: 36