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

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

Neuron 4854 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0324. Min Range: -3.0324

Max Act: 3.0324. Min Act: -0.0000

Data Index: 1124738 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 3.0324. Min Range: -3.0324

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1015978 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.8311. Min Act: -0.0000

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.6760. Min Act: -0.0000

Data Index: 225686 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.8018. Min Act: -0.0000

Data Index: 228066 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7813. Min Act: -0.0000

Data Index: 1113644 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.8828. Min Act: -0.0000

Data Index: 1227365 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7682. Min Act: -0.0000

Data Index: 1236965 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7525. Min Act: -0.0000

Data Index: 884933 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7552. Min Act: -0.0000

Data Index: 419621 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7376. Min Act: -0.0000

Data Index: 992819 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7593. Min Act: -0.0000

Data Index: 1007260 (C4 (Web Text))

Max Activating Token Index: 803

Text #12

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7363. Min Act: -0.0000

Data Index: 1207217 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.6027. Min Act: -0.0000

Data Index: 1229690 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.8311. Min Act: -0.0000

Data Index: 719402 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.8429. Min Act: -0.0000

Data Index: 1160620 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.6811. Min Act: -0.0000

Data Index: 619155 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.6862. Min Act: -0.0000

Data Index: 914785 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.6770. Min Act: -0.0000

Data Index: 23973 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 3.0324. Min Range: -3.0324

Max Act: 2.7019. Min Act: -0.0000

Data Index: 406824 (C4 (Web Text))

Max Activating Token Index: 641