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

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

Neuron 2376 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.7705. Min Act: -0.0000

Data Index: 265030 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.8746. Min Act: -0.0000

Data Index: 246952 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.7536. Min Act: -0.0000

Data Index: 355127 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.7028. Min Act: -0.0000

Data Index: 158445 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1370433 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.6464. Min Act: -0.0000

Data Index: 761317 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.6013. Min Act: 0.0000

Data Index: 287376 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.6463. Min Act: -0.0000

Data Index: 1495225 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.6386. Min Act: -0.0000

Data Index: 1184948 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5910. Min Act: -0.0000

Data Index: 888027 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1371870 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.6019. Min Act: -0.0000

Data Index: 502 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5776. Min Act: -0.0000

Data Index: 1031956 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1153628 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1486878 (Python Code)

Max Activating Token Index: 618

Text #15

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1044271 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5634. Min Act: -0.0000

Data Index: 851940 (C4 (Web Text))

Max Activating Token Index: 467

Text #17

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1230780 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1638855 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 0.8746. Min Range: -0.8746

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1256178 (C4 (Web Text))

Max Activating Token Index: 582