Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 889 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1505235 (Python Code)

Max Activating Token Index: 698

Text #1

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0902. Min Act: -0.0001

Data Index: 440101 (C4 (Web Text))

Max Activating Token Index: 873

Text #2

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1531693 (Python Code)

Max Activating Token Index: 742

Text #3

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0934. Min Act: -0.0001

Data Index: 96245 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0852. Min Act: -0.0001

Data Index: 678806 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0867. Min Act: -0.0001

Data Index: 664687 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0827. Min Act: -0.0001

Data Index: 439595 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1247540 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1355463 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0850. Min Act: -0.0001

Data Index: 901666 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0813. Min Act: -0.0001

Data Index: 989345 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0697. Min Act: -0.0001

Data Index: 17241 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0873. Min Act: -0.0001

Data Index: 848667 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1464720 (Python Code)

Max Activating Token Index: 11

Text #14

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1197764 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0854. Min Act: -0.0001

Data Index: 1572044 (Python Code)

Max Activating Token Index: 192

Text #16

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1385765 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0841. Min Act: -0.0001

Data Index: 1117068 (C4 (Web Text))

Max Activating Token Index: 382

Text #18

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1594845 (Python Code)

Max Activating Token Index: 763

Text #19

Max Range: 0.1023. Min Range: -0.1023

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1079297 (C4 (Web Text))

Max Activating Token Index: 237