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

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

Neuron 2818 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: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1594282 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0611. Min Act: -0.0002

Data Index: 1471023 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0493. Min Act: -0.0002

Data Index: 822265 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1167358 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0313. Min Act: -0.0002

Data Index: 525510 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0307. Min Act: -0.0002

Data Index: 284015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1517373 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1655450 (Python Code)

Max Activating Token Index: 1021

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0289. Min Act: -0.0003

Data Index: 222815 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1138870 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0287. Min Act: -0.0002

Data Index: 380833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0274. Min Act: -0.0002

Data Index: 368557 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0282. Min Act: -0.0002

Data Index: 969919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0272. Min Act: -0.0003

Data Index: 456544 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0262. Min Act: -0.0002

Data Index: 137340 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0268. Min Act: -0.0002

Data Index: 437357 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1072077 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0252. Min Act: -0.0002

Data Index: 582556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0253. Min Act: -0.0002

Data Index: 428126 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0259. Min Act: -0.0002

Data Index: 1067745 (C4 (Web Text))

Max Activating Token Index: 1023