Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 856 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0538. Min Act: -0.0001

Data Index: 569107 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0486. Min Act: -0.0001

Data Index: 325855 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0393. Min Act: -0.0001

Data Index: 203325 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0316. Min Act: -0.0001

Data Index: 370851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0269. Min Act: -0.0001

Data Index: 294545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0300. Min Act: -0.0001

Data Index: 545072 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0112. Min Act: -0.0001

Data Index: 1569812 (Python Code)

Max Activating Token Index: 971

Text #7

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0253. Min Act: -0.0001

Data Index: 347980 (C4 (Web Text))

Max Activating Token Index: 1010

Text #8

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0239. Min Act: -0.0001

Data Index: 56687 (C4 (Web Text))

Max Activating Token Index: 1007

Text #9

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0226. Min Act: -0.0001

Data Index: 1486078 (Python Code)

Max Activating Token Index: 1019

Text #10

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1277062 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0169. Min Act: -0.0001

Data Index: 1560275 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0205. Min Act: -0.0001

Data Index: 877499 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0212. Min Act: -0.0001

Data Index: 637708 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0197. Min Act: -0.0001

Data Index: 1390093 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0213. Min Act: -0.0001

Data Index: 714401 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0222. Min Act: -0.0001

Data Index: 1638789 (Python Code)

Max Activating Token Index: 1011

Text #17

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1478762 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0216. Min Act: -0.0001

Data Index: 1344242 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0538. Min Range: -0.0538

Max Act: 0.0196. Min Act: -0.0001

Data Index: 1440444 (Python Code)

Max Activating Token Index: 1022