Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1222 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2047. Min Range: -1.2047

Max Act: 1.2047. Min Act: -0.0001

Data Index: 1182687 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.9409. Min Act: -0.0001

Data Index: 894772 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8940. Min Act: -0.0001

Data Index: 1244739 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8256. Min Act: -0.0001

Data Index: 1190202 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8604. Min Act: -0.0001

Data Index: 241194 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8499. Min Act: -0.0001

Data Index: 52208 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8323. Min Act: -0.0001

Data Index: 314618 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7843. Min Act: -0.0001

Data Index: 546469 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8261. Min Act: -0.0001

Data Index: 161004 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8416. Min Act: -0.0001

Data Index: 656964 (C4 (Web Text))

Max Activating Token Index: 594

Text #10

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7983. Min Act: -0.0001

Data Index: 796580 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8178. Min Act: -0.0001

Data Index: 1229601 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8498. Min Act: -0.0001

Data Index: 898803 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8082. Min Act: -0.0001

Data Index: 512630 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8068. Min Act: -0.0001

Data Index: 1332848 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7778. Min Act: -0.0001

Data Index: 554104 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.8015. Min Act: -0.0001

Data Index: 1156338 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1108464 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1124548 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 1.2047. Min Range: -1.2047

Max Act: 0.7916. Min Act: -0.0001

Data Index: 1021385 (C4 (Web Text))

Max Activating Token Index: 711