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

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

Neuron 598 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0865. Min Range: -1.0865

Max Act: 1.0865. Min Act: -0.0001

Data Index: 1211285 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8690. Min Act: -0.0001

Data Index: 907266 (C4 (Web Text))

Max Activating Token Index: 522

Text #2

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.9157. Min Act: -0.0001

Data Index: 146206 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8378. Min Act: -0.0001

Data Index: 1290815 (C4 (Web Text))

Max Activating Token Index: 491

Text #4

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.8489. Min Act: -0.0001

Data Index: 699672 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7881. Min Act: -0.0001

Data Index: 529934 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7455. Min Act: -0.0001

Data Index: 1303989 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6742. Min Act: -0.0001

Data Index: 685287 (C4 (Web Text))

Max Activating Token Index: 37

Text #8

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6847. Min Act: -0.0001

Data Index: 39245 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7335. Min Act: -0.0001

Data Index: 359234 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7048. Min Act: -0.0001

Data Index: 1136586 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.7102. Min Act: -0.0001

Data Index: 350492 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6739. Min Act: -0.0001

Data Index: 159907 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6773. Min Act: -0.0001

Data Index: 1177523 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6534. Min Act: -0.0001

Data Index: 1270777 (C4 (Web Text))

Max Activating Token Index: 132

Text #15

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6689. Min Act: -0.0001

Data Index: 1308135 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6725. Min Act: -0.0001

Data Index: 949379 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6817. Min Act: -0.0001

Data Index: 1018145 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6774. Min Act: -0.0001

Data Index: 701686 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 1.0865. Min Range: -1.0865

Max Act: 0.6458. Min Act: -0.0001

Data Index: 360103 (C4 (Web Text))

Max Activating Token Index: 907