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

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

Neuron 369 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0306. Min Act: -0.0004

Data Index: 686911 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0320. Min Act: -0.0004

Data Index: 591778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1416335 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1612982 (Python Code)

Max Activating Token Index: 958

Text #4

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0295. Min Act: -0.0004

Data Index: 279984 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0297. Min Act: -0.0004

Data Index: 737508 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0295. Min Act: -0.0004

Data Index: 1441823 (Python Code)

Max Activating Token Index: 954

Text #7

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0269. Min Act: -0.0004

Data Index: 672863 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0278. Min Act: -0.0004

Data Index: 839588 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0271. Min Act: -0.0004

Data Index: 773509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0267. Min Act: -0.0004

Data Index: 257429 (C4 (Web Text))

Max Activating Token Index: 1007

Text #11

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0272. Min Act: -0.0004

Data Index: 310452 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0266. Min Act: -0.0004

Data Index: 160046 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0282. Min Act: -0.0004

Data Index: 1259724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1505939 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1654049 (Python Code)

Max Activating Token Index: 926

Text #16

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1589720 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1621341 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0251. Min Act: -0.0005

Data Index: 397428 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 0.0320. Min Range: -0.0320

Max Act: 0.0257. Min Act: -0.0004

Data Index: 862132 (C4 (Web Text))

Max Activating Token Index: 915