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

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

Neuron 4356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.1771. Min Act: -0.0002

Data Index: 132848 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.2123. Min Act: -0.0002

Data Index: 1211639 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0756. Min Act: -0.0002

Data Index: 981735 (C4 (Web Text))

Max Activating Token Index: 426

Text #3

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.3004. Min Act: -0.0002

Data Index: 1641690 (Python Code)

Max Activating Token Index: 168

Text #4

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.1644. Min Act: -0.0002

Data Index: 761089 (C4 (Web Text))

Max Activating Token Index: 599

Text #5

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.1419. Min Act: -0.0002

Data Index: 166699 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.1001. Min Act: -0.0002

Data Index: 1489340 (Python Code)

Max Activating Token Index: 585

Text #7

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.1671. Min Act: -0.0002

Data Index: 1441611 (Python Code)

Max Activating Token Index: 888

Text #8

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0452. Min Act: -0.0002

Data Index: 766788 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0756. Min Act: -0.0002

Data Index: 1597300 (Python Code)

Max Activating Token Index: 345

Text #10

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.2012. Min Act: -0.0002

Data Index: 110238 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0827. Min Act: -0.0002

Data Index: 15602 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0880. Min Act: -0.0002

Data Index: 281484 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0413. Min Act: -0.0002

Data Index: 141752 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0427. Min Act: -0.0002

Data Index: 1554762 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 1.3004. Min Range: -1.3004

Max Act: 0.9973. Min Act: -0.0002

Data Index: 822604 (C4 (Web Text))

Max Activating Token Index: 622

Text #16

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0022. Min Act: -0.0002

Data Index: 1208359 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.3004. Min Range: -1.3004

Max Act: 1.0635. Min Act: -0.0002

Data Index: 155897 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 1.3004. Min Range: -1.3004

Max Act: 0.8771. Min Act: -0.0002

Data Index: 413346 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 1.3004. Min Range: -1.3004

Max Act: 0.9986. Min Act: -0.0002

Data Index: 659260 (C4 (Web Text))

Max Activating Token Index: 151