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

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

Neuron 691 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: 0.0297. Min Range: -0.0297

Max Act: 0.0286. Min Act: -0.0004

Data Index: 858174 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0004

Data Index: 196009 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0273. Min Act: -0.0004

Data Index: 96690 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0272. Min Act: -0.0004

Data Index: 663096 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0269. Min Act: -0.0004

Data Index: 911967 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0258. Min Act: -0.0004

Data Index: 643594 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0256. Min Act: -0.0004

Data Index: 634962 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0255. Min Act: -0.0004

Data Index: 249500 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0265. Min Act: -0.0004

Data Index: 624350 (C4 (Web Text))

Max Activating Token Index: 847

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0276. Min Act: -0.0004

Data Index: 56025 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0252. Min Act: -0.0004

Data Index: 882876 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0247. Min Act: -0.0004

Data Index: 553555 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0252. Min Act: -0.0004

Data Index: 165832 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0261. Min Act: -0.0004

Data Index: 536933 (C4 (Web Text))

Max Activating Token Index: 771

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0233. Min Act: -0.0004

Data Index: 363975 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0244. Min Act: -0.0004

Data Index: 529980 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0259. Min Act: -0.0004

Data Index: 612657 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0249. Min Act: -0.0004

Data Index: 315271 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0235. Min Act: -0.0004

Data Index: 392888 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0253. Min Act: -0.0004

Data Index: 258335 (C4 (Web Text))

Max Activating Token Index: 444