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

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

Neuron 1842 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1406865 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1404595 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0353. Min Act: -0.0003

Data Index: 1565205 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0358. Min Act: -0.0002

Data Index: 1570530 (Python Code)

Max Activating Token Index: 897

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1380357 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1369558 (Python Code)

Max Activating Token Index: 292

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1617753 (Python Code)

Max Activating Token Index: 1009

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0332. Min Act: -0.0002

Data Index: 1484052 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0324. Min Act: -0.0003

Data Index: 1537176 (Python Code)

Max Activating Token Index: 233

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1515873 (Python Code)

Max Activating Token Index: 974

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1402938 (Python Code)

Max Activating Token Index: 628

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1527422 (Python Code)

Max Activating Token Index: 534

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1575305 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0319. Min Act: -0.0002

Data Index: 1480817 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1633412 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1450929 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1419143 (Python Code)

Max Activating Token Index: 879

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1629118 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1389124 (Python Code)

Max Activating Token Index: 754

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1601221 (Python Code)

Max Activating Token Index: 535