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

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

Neuron 4681 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7453. Min Act: -0.0003

Data Index: 977840 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7251. Min Act: -0.0003

Data Index: 194917 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7147. Min Act: -0.0003

Data Index: 974952 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7376. Min Act: -0.0003

Data Index: 988911 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7006. Min Act: -0.0003

Data Index: 509360 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7242. Min Act: -0.0003

Data Index: 510267 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6915. Min Act: -0.0003

Data Index: 278429 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6983. Min Act: -0.0003

Data Index: 1257483 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6796. Min Act: -0.0003

Data Index: 1005083 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6892. Min Act: -0.0003

Data Index: 1151010 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.7009. Min Act: -0.0003

Data Index: 393088 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6886. Min Act: -0.0003

Data Index: 935832 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6747. Min Act: -0.0003

Data Index: 359373 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6821. Min Act: -0.0003

Data Index: 117950 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6586. Min Act: -0.0003

Data Index: 1091411 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6795. Min Act: -0.0003

Data Index: 284239 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6772. Min Act: -0.0003

Data Index: 1078893 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6861. Min Act: -0.0003

Data Index: 474831 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6653. Min Act: -0.0003

Data Index: 950151 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.7453. Min Range: -0.7453

Max Act: 0.6743. Min Act: -0.0003

Data Index: 1335723 (C4 (Web Text))

Max Activating Token Index: 30