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

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

Neuron 4847 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.8981. Min Act: -0.0000

Data Index: 1289525 (C4 (Web Text))

Max Activating Token Index: 240

Text #1

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.6361. Min Act: -0.0000

Data Index: 1037425 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.7950. Min Act: -0.0000

Data Index: 447020 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4596. Min Act: -0.0000

Data Index: 31944 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.7089. Min Act: -0.0000

Data Index: 106181 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4541. Min Act: -0.0000

Data Index: 116068 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4226. Min Act: -0.0000

Data Index: 1158748 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.5015. Min Act: -0.0000

Data Index: 566514 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4803. Min Act: -0.0000

Data Index: 220697 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4182. Min Act: -0.0000

Data Index: 35074 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.5567. Min Act: -0.0000

Data Index: 356405 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4467. Min Act: -0.0000

Data Index: 1310779 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.3322. Min Act: -0.0000

Data Index: 1273275 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.5308. Min Act: -0.0000

Data Index: 1187029 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4195. Min Act: -0.0000

Data Index: 982751 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4581. Min Act: -0.0000

Data Index: 806505 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4213. Min Act: -0.0000

Data Index: 378827 (C4 (Web Text))

Max Activating Token Index: 920

Text #17

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4143. Min Act: -0.0000

Data Index: 927588 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.4274. Min Act: -0.0000

Data Index: 996271 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 1.8981. Min Range: -1.8981

Max Act: 1.3761. Min Act: -0.0000

Data Index: 956446 (C4 (Web Text))

Max Activating Token Index: 904