Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2871 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.9340. Min Act: -0.0003

Data Index: 1263452 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.8147. Min Act: -0.0003

Data Index: 907013 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7666. Min Act: -0.0003

Data Index: 346146 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7048. Min Act: -0.0003

Data Index: 1397365 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.7476. Min Act: -0.0003

Data Index: 825787 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6760. Min Act: -0.0003

Data Index: 887260 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6632. Min Act: -0.0003

Data Index: 475753 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6498. Min Act: -0.0003

Data Index: 726484 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6858. Min Act: -0.0003

Data Index: 1230411 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6712. Min Act: -0.0003

Data Index: 462498 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6584. Min Act: -0.0003

Data Index: 217224 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6954. Min Act: -0.0003

Data Index: 858215 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6663. Min Act: -0.0003

Data Index: 1353845 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6375. Min Act: -0.0003

Data Index: 187293 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6306. Min Act: -0.0003

Data Index: 1333290 (C4 (Web Text))

Max Activating Token Index: 520

Text #15

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6614. Min Act: -0.0003

Data Index: 876641 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6245. Min Act: -0.0003

Data Index: 1284707 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6408. Min Act: -0.0003

Data Index: 605015 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6157. Min Act: -0.0003

Data Index: 1058327 (C4 (Web Text))

Max Activating Token Index: 368

Text #19

Max Range: 0.9340. Min Range: -0.9340

Max Act: 0.6263. Min Act: -0.0003

Data Index: 622469 (C4 (Web Text))

Max Activating Token Index: 361