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

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

Neuron 354 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.3080. Min Act: -0.0000

Data Index: 413108 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1746. Min Act: -0.0000

Data Index: 838461 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0837. Min Act: 0.0000

Data Index: 1304901 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.0065. Min Act: -0.0000

Data Index: 199757 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9541. Min Act: -0.0000

Data Index: 474099 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1137651 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8593. Min Act: -0.0000

Data Index: 48139 (C4 (Web Text))

Max Activating Token Index: 991

Text #7

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8550. Min Act: 0.0000

Data Index: 985859 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1210727 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8215. Min Act: -0.0000

Data Index: 712892 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7670. Min Act: -0.0000

Data Index: 61972 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7402. Min Act: -0.0000

Data Index: 191173 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.6722. Min Act: -0.0000

Data Index: 423534 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7089. Min Act: -0.0000

Data Index: 766962 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7005. Min Act: -0.0000

Data Index: 562809 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.6830. Min Act: -0.0000

Data Index: 986387 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.6913. Min Act: -0.0000

Data Index: 791698 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.6402. Min Act: -0.0000

Data Index: 359201 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.6777. Min Act: -0.0000

Data Index: 828396 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1044945 (C4 (Web Text))

Max Activating Token Index: 505