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

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

Neuron 5128 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: 0.1265. Min Range: -0.1265

Max Act: 0.1265. Min Act: -0.0000

Data Index: 449575 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1101. Min Act: -0.0000

Data Index: 654047 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1314878 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.1062. Min Act: -0.0000

Data Index: 430903 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0948. Min Act: -0.0000

Data Index: 917901 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0977. Min Act: -0.0000

Data Index: 207093 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0946. Min Act: -0.0000

Data Index: 446886 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0877. Min Act: -0.0000

Data Index: 980252 (C4 (Web Text))

Max Activating Token Index: 583

Text #8

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0849. Min Act: -0.0000

Data Index: 369961 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0819. Min Act: -0.0000

Data Index: 631081 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0814. Min Act: -0.0001

Data Index: 1219977 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0803. Min Act: -0.0000

Data Index: 25157 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0837. Min Act: -0.0000

Data Index: 371834 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0853. Min Act: -0.0000

Data Index: 365980 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0851. Min Act: -0.0001

Data Index: 590111 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0779. Min Act: -0.0000

Data Index: 854414 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1228577 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0722. Min Act: -0.0000

Data Index: 555317 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0747. Min Act: -0.0000

Data Index: 775754 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 0.1265. Min Range: -0.1265

Max Act: 0.0720. Min Act: -0.0000

Data Index: 154518 (C4 (Web Text))

Max Activating Token Index: 840