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

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

Neuron 3440 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: 0.0743. Min Range: -0.0743

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1188042 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0649. Min Act: -0.0002

Data Index: 467939 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0452. Min Act: -0.0002

Data Index: 902857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0414. Min Act: -0.0002

Data Index: 992975 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0485. Min Act: -0.0002

Data Index: 118340 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0526. Min Act: -0.0002

Data Index: 464590 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1278154 (C4 (Web Text))

Max Activating Token Index: 28

Text #7

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0529. Min Act: -0.0002

Data Index: 10387 (C4 (Web Text))

Max Activating Token Index: 108

Text #8

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0423. Min Act: -0.0002

Data Index: 893165 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0400. Min Act: -0.0002

Data Index: 129230 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0352. Min Act: -0.0002

Data Index: 346621 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0379. Min Act: -0.0002

Data Index: 1267136 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0435. Min Act: -0.0002

Data Index: 282825 (C4 (Web Text))

Max Activating Token Index: 174

Text #13

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0478. Min Act: -0.0002

Data Index: 1286756 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0499. Min Act: -0.0002

Data Index: 1133410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0382. Min Act: -0.0002

Data Index: 245160 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0435. Min Act: -0.0002

Data Index: 520599 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0463. Min Act: -0.0002

Data Index: 365587 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0404. Min Act: -0.0002

Data Index: 335439 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.0743. Min Range: -0.0743

Max Act: 0.0313. Min Act: -0.0002

Data Index: 499842 (C4 (Web Text))

Max Activating Token Index: 630