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

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

Neuron 3857 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: 1.2655. Min Range: -1.2655

Max Act: 1.2377. Min Act: -0.0001

Data Index: 1225327 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.2655. Min Act: -0.0001

Data Index: 1304886 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.2016. Min Act: -0.0001

Data Index: 84506 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1692. Min Act: -0.0001

Data Index: 438067 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1745. Min Act: -0.0001

Data Index: 321043 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1680. Min Act: -0.0001

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0881. Min Act: -0.0001

Data Index: 600213 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0894. Min Act: -0.0001

Data Index: 661278 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1192. Min Act: -0.0001

Data Index: 692800 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1178. Min Act: -0.0001

Data Index: 101382 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1366. Min Act: -0.0001

Data Index: 1145496 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1323. Min Act: -0.0001

Data Index: 1011958 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1480. Min Act: -0.0001

Data Index: 992626 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1069. Min Act: -0.0001

Data Index: 216360 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1458. Min Act: -0.0001

Data Index: 110047 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0849. Min Act: -0.0001

Data Index: 1144013 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0508. Min Act: -0.0001

Data Index: 996611 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.1055. Min Act: -0.0001

Data Index: 626964 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0671. Min Act: -0.0001

Data Index: 332803 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.2655. Min Range: -1.2655

Max Act: 1.0210. Min Act: -0.0001

Data Index: 197202 (C4 (Web Text))

Max Activating Token Index: 62