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

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

Neuron 5318 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.6994. Min Act: -0.0001

Data Index: 926475 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5455. Min Act: -0.0001

Data Index: 240599 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5316. Min Act: -0.0001

Data Index: 1187449 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.5139. Min Act: -0.0001

Data Index: 1238830 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4790. Min Act: -0.0001

Data Index: 54275 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4530. Min Act: -0.0001

Data Index: 1045199 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4632. Min Act: -0.0001

Data Index: 1315522 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1090771 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4339. Min Act: -0.0001

Data Index: 1025191 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4477. Min Act: -0.0001

Data Index: 871726 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4307. Min Act: -0.0001

Data Index: 60985 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4209. Min Act: -0.0001

Data Index: 941264 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4296. Min Act: -0.0001

Data Index: 180684 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4229. Min Act: -0.0001

Data Index: 1063344 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4138. Min Act: -0.0001

Data Index: 12911 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1185925 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3867. Min Act: -0.0001

Data Index: 266726 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.3976. Min Act: -0.0001

Data Index: 451766 (C4 (Web Text))

Max Activating Token Index: 879

Text #18

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4100. Min Act: -0.0001

Data Index: 429863 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.6994. Min Range: -0.6994

Max Act: 0.4097. Min Act: -0.0001

Data Index: 806166 (C4 (Web Text))

Max Activating Token Index: 573