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

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

Neuron 4460 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: 1.4080. Min Range: -1.4080

Max Act: 1.4080. Min Act: -0.0000

Data Index: 895265 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 1.4080. Min Range: -1.4080

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1290746 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9508. Min Act: -0.0000

Data Index: 1305371 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1168717 (C4 (Web Text))

Max Activating Token Index: 952

Text #4

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8915. Min Act: -0.0000

Data Index: 534959 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.9059. Min Act: -0.0000

Data Index: 360122 (C4 (Web Text))

Max Activating Token Index: 235

Text #6

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8500. Min Act: -0.0000

Data Index: 396403 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8430. Min Act: -0.0000

Data Index: 671162 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8704. Min Act: -0.0000

Data Index: 1113518 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8858. Min Act: -0.0000

Data Index: 992149 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8447. Min Act: -0.0000

Data Index: 743703 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8523. Min Act: -0.0000

Data Index: 758330 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1243941 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8286. Min Act: -0.0000

Data Index: 740786 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8711. Min Act: -0.0001

Data Index: 626236 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8128. Min Act: -0.0000

Data Index: 295855 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.8545. Min Act: -0.0000

Data Index: 708064 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.7175. Min Act: -0.0000

Data Index: 178416 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.7900. Min Act: -0.0000

Data Index: 977656 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 1.4080. Min Range: -1.4080

Max Act: 0.7880. Min Act: -0.0001

Data Index: 787301 (C4 (Web Text))

Max Activating Token Index: 356