Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 618 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0473. Min Act: -0.0004

Data Index: 817605 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0360. Min Act: -0.0004

Data Index: 949204 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0279. Min Act: -0.0004

Data Index: 1305166 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0270. Min Act: -0.0004

Data Index: 297960 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0272. Min Act: -0.0004

Data Index: 1159253 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0231. Min Act: -0.0004

Data Index: 679385 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0262. Min Act: -0.0004

Data Index: 145496 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1646 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0255. Min Act: -0.0004

Data Index: 243348 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0252. Min Act: -0.0004

Data Index: 783835 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0249. Min Act: -0.0004

Data Index: 712861 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0269. Min Act: -0.0004

Data Index: 618887 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0248. Min Act: -0.0004

Data Index: 259141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0256. Min Act: -0.0004

Data Index: 979143 (C4 (Web Text))

Max Activating Token Index: 522

Text #14

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0235. Min Act: -0.0004

Data Index: 839615 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0235. Min Act: -0.0004

Data Index: 1458530 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0228. Min Act: -0.0004

Data Index: 866105 (C4 (Web Text))

Max Activating Token Index: 26

Text #17

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0220. Min Act: -0.0004

Data Index: 947345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0229. Min Act: -0.0004

Data Index: 564691 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0473. Min Range: -0.0473

Max Act: 0.0218. Min Act: -0.0004

Data Index: 1009542 (C4 (Web Text))

Max Activating Token Index: 1023