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

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

Neuron 594 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: 0.0847. Min Range: -0.0847

Max Act: 0.0842. Min Act: -0.0001

Data Index: 544906 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1048765 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0790. Min Act: -0.0001

Data Index: 65773 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0847. Min Act: -0.0001

Data Index: 841344 (C4 (Web Text))

Max Activating Token Index: 561

Text #4

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0765. Min Act: -0.0001

Data Index: 1095982 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0689. Min Act: -0.0001

Data Index: 954253 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0686. Min Act: -0.0001

Data Index: 30208 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0655. Min Act: -0.0001

Data Index: 1132182 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0705. Min Act: -0.0001

Data Index: 63671 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0679. Min Act: -0.0001

Data Index: 330535 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1056517 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0684. Min Act: -0.0001

Data Index: 451092 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1080816 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1070369 (C4 (Web Text))

Max Activating Token Index: 469

Text #14

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0693. Min Act: -0.0001

Data Index: 641994 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0647. Min Act: -0.0001

Data Index: 280459 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1420996 (Python Code)

Max Activating Token Index: 1010

Text #17

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0662. Min Act: -0.0001

Data Index: 169270 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0627. Min Act: -0.0001

Data Index: 955186 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0847. Min Range: -0.0847

Max Act: 0.0652. Min Act: -0.0001

Data Index: 368796 (C4 (Web Text))

Max Activating Token Index: 133