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

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

Neuron 430 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0267. Min Act: -0.0001

Data Index: 629509 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0275. Min Act: -0.0001

Data Index: 431650 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0201. Min Act: -0.0001

Data Index: 1481760 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0203. Min Act: -0.0001

Data Index: 1373471 (Python Code)

Max Activating Token Index: 941

Text #4

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0183. Min Act: -0.0001

Data Index: 551826 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0191. Min Act: -0.0001

Data Index: 491882 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0182. Min Act: -0.0001

Data Index: 928525 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0184. Min Act: -0.0001

Data Index: 1609200 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0169. Min Act: -0.0001

Data Index: 325120 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1584753 (Python Code)

Max Activating Token Index: 967

Text #10

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0168. Min Act: -0.0001

Data Index: 474841 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0172. Min Act: -0.0001

Data Index: 1612956 (Python Code)

Max Activating Token Index: 1013

Text #12

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0164. Min Act: -0.0001

Data Index: 631354 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0165. Min Act: -0.0001

Data Index: 1142721 (C4 (Web Text))

Max Activating Token Index: 1015

Text #14

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0157. Min Act: -0.0001

Data Index: 513275 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0160. Min Act: -0.0001

Data Index: 772160 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0151. Min Act: -0.0001

Data Index: 603064 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0151. Min Act: -0.0001

Data Index: 407655 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1561531 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0151. Min Act: -0.0001

Data Index: 375074 (C4 (Web Text))

Max Activating Token Index: 1023