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

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

Neuron 3116 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: 0.8690. Min Range: -0.8690

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1153178 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7874. Min Act: -0.0000

Data Index: 1203082 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1008391 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7575. Min Act: -0.0000

Data Index: 913222 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7656. Min Act: -0.0000

Data Index: 115846 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7516. Min Act: -0.0000

Data Index: 665106 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7367. Min Act: -0.0000

Data Index: 575638 (C4 (Web Text))

Max Activating Token Index: 251

Text #7

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6712. Min Act: -0.0000

Data Index: 304453 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1143413 (C4 (Web Text))

Max Activating Token Index: 527

Text #9

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1166839 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6461. Min Act: -0.0000

Data Index: 84151 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6665. Min Act: -0.0000

Data Index: 932278 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6838. Min Act: -0.0000

Data Index: 751831 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.7228. Min Act: -0.0000

Data Index: 736393 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6602. Min Act: -0.0000

Data Index: 699391 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1290758 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6787. Min Act: -0.0000

Data Index: 506068 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6605. Min Act: -0.0000

Data Index: 763294 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6286. Min Act: -0.0000

Data Index: 206738 (C4 (Web Text))

Max Activating Token Index: 134

Text #19

Max Range: 0.8690. Min Range: -0.8690

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1240953 (C4 (Web Text))

Max Activating Token Index: 57