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

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

Neuron 369 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4250. Min Range: -2.4250

Max Act: 2.4250. Min Act: -0.0000

Data Index: 447386 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.8811. Min Act: -0.0000

Data Index: 420623 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.7989. Min Act: -0.0000

Data Index: 185171 (C4 (Web Text))

Max Activating Token Index: 417

Text #3

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.7833. Min Act: -0.0000

Data Index: 1048184 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.7296. Min Act: -0.0000

Data Index: 895731 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.6471. Min Act: -0.0000

Data Index: 1007057 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.6358. Min Act: -0.0000

Data Index: 820779 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5596. Min Act: -0.0000

Data Index: 857555 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.6282. Min Act: -0.0000

Data Index: 51466 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5966. Min Act: -0.0000

Data Index: 1115522 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.6058. Min Act: -0.0000

Data Index: 60434 (C4 (Web Text))

Max Activating Token Index: 753

Text #11

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.6050. Min Act: -0.0000

Data Index: 1215376 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5006. Min Act: -0.0000

Data Index: 830423 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5413. Min Act: -0.0000

Data Index: 288422 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5653. Min Act: -0.0000

Data Index: 428651 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.4573. Min Act: -0.0000

Data Index: 1640522 (Python Code)

Max Activating Token Index: 140

Text #16

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1653768 (Python Code)

Max Activating Token Index: 648

Text #17

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5215. Min Act: -0.0000

Data Index: 669616 (C4 (Web Text))

Max Activating Token Index: 1018

Text #18

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.6049. Min Act: -0.0000

Data Index: 1172744 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 2.4250. Min Range: -2.4250

Max Act: 1.5159. Min Act: -0.0000

Data Index: 1536810 (Python Code)

Max Activating Token Index: 708