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

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

Neuron 3955 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.9471. Min Act: -0.0000

Data Index: 652511 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.5984. Min Act: -0.0000

Data Index: 414949 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.6584. Min Act: -0.0000

Data Index: 283596 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.5081. Min Act: -0.0000

Data Index: 1016831 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.5291. Min Act: -0.0000

Data Index: 403235 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.4287. Min Act: -0.0000

Data Index: 739726 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.3711. Min Act: -0.0000

Data Index: 597581 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.2687. Min Act: -0.0000

Data Index: 290230 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.4342. Min Act: -0.0000

Data Index: 1289842 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.3317. Min Act: -0.0000

Data Index: 10245 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.3122. Min Act: -0.0000

Data Index: 630585 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.3852. Min Act: -0.0000

Data Index: 620955 (C4 (Web Text))

Max Activating Token Index: 626

Text #12

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.3462. Min Act: -0.0000

Data Index: 660441 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.2835. Min Act: -0.0000

Data Index: 635608 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.2306. Min Act: -0.0000

Data Index: 785561 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.1491. Min Act: -0.0000

Data Index: 1113737 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.1941. Min Act: -0.0000

Data Index: 4263 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.1901. Min Act: -0.0000

Data Index: 603930 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.1962. Min Act: -0.0000

Data Index: 858293 (C4 (Web Text))

Max Activating Token Index: 497

Text #19

Max Range: 1.9471. Min Range: -1.9471

Max Act: 1.1721. Min Act: -0.0000

Data Index: 889349 (C4 (Web Text))

Max Activating Token Index: 138