Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4930 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4600. Min Act: -0.0000

Data Index: 851617 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4124. Min Act: -0.0000

Data Index: 965756 (C4 (Web Text))

Max Activating Token Index: 118

Text #2

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1190776 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4096. Min Act: -0.0000

Data Index: 186034 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3982. Min Act: -0.0000

Data Index: 1282388 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3742. Min Act: -0.0000

Data Index: 828736 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3732. Min Act: -0.0000

Data Index: 638606 (C4 (Web Text))

Max Activating Token Index: 121

Text #7

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.4009. Min Act: -0.0000

Data Index: 150850 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3765. Min Act: -0.0000

Data Index: 197558 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3773. Min Act: -0.0000

Data Index: 488341 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3462. Min Act: -0.0000

Data Index: 20717 (C4 (Web Text))

Max Activating Token Index: 527

Text #11

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3557. Min Act: -0.0000

Data Index: 1038793 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3760. Min Act: -0.0000

Data Index: 322926 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3525. Min Act: -0.0000

Data Index: 257588 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3355. Min Act: -0.0000

Data Index: 222228 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3312. Min Act: -0.0000

Data Index: 987542 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3295. Min Act: -0.0000

Data Index: 214890 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3219. Min Act: -0.0000

Data Index: 76389 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3510. Min Act: -0.0000

Data Index: 110358 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 0.4600. Min Range: -0.4600

Max Act: 0.3176. Min Act: -0.0000

Data Index: 230442 (C4 (Web Text))

Max Activating Token Index: 354