Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1840 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1478197 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0477. Min Act: -0.0006

Data Index: 1442516 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0458. Min Act: -0.0006

Data Index: 1383498 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0386. Min Act: -0.0006

Data Index: 1429295 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0378. Min Act: -0.0006

Data Index: 1418397 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0355. Min Act: -0.0006

Data Index: 1395360 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1638890 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0351. Min Act: -0.0006

Data Index: 1518874 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0334. Min Act: -0.0006

Data Index: 1499572 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0323. Min Act: -0.0006

Data Index: 112951 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0325. Min Act: -0.0006

Data Index: 1444435 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0327. Min Act: -0.0006

Data Index: 1638286 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0327. Min Act: -0.0006

Data Index: 1654001 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1382684 (Python Code)

Max Activating Token Index: 1009

Text #14

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0309. Min Act: -0.0006

Data Index: 1380147 (Python Code)

Max Activating Token Index: 973

Text #15

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1467579 (Python Code)

Max Activating Token Index: 979

Text #16

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0317. Min Act: -0.0005

Data Index: 1654012 (Python Code)

Max Activating Token Index: 921

Text #17

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0308. Min Act: -0.0006

Data Index: 1454344 (Python Code)

Max Activating Token Index: 834

Text #18

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0294. Min Act: -0.0006

Data Index: 1385136 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0481. Min Range: -0.0481

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1569725 (Python Code)

Max Activating Token Index: 682