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

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

Neuron 2021 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: 0.5467. Min Range: -0.5467

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1016939 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4757. Min Act: -0.0000

Data Index: 881097 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4672. Min Act: -0.0001

Data Index: 687124 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4647. Min Act: -0.0001

Data Index: 1170223 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3991. Min Act: -0.0001

Data Index: 999464 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4052. Min Act: -0.0000

Data Index: 98261 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4175. Min Act: -0.0001

Data Index: 414877 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3979. Min Act: -0.0000

Data Index: 555428 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4085. Min Act: -0.0000

Data Index: 115688 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3935. Min Act: -0.0000

Data Index: 71679 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.4042. Min Act: -0.0000

Data Index: 304897 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3852. Min Act: -0.0000

Data Index: 36823 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3996. Min Act: -0.0000

Data Index: 522702 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3963. Min Act: -0.0000

Data Index: 12556 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3925. Min Act: -0.0000

Data Index: 396184 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3789. Min Act: -0.0000

Data Index: 441909 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1198443 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3817. Min Act: -0.0001

Data Index: 545114 (C4 (Web Text))

Max Activating Token Index: 778

Text #18

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3912. Min Act: -0.0000

Data Index: 409160 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 0.5467. Min Range: -0.5467

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1074121 (C4 (Web Text))

Max Activating Token Index: 856