Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6043 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8681. Min Act: -0.0000

Data Index: 66517 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.8265. Min Act: -0.0000

Data Index: 901704 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.7504. Min Act: -0.0000

Data Index: 445393 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6883. Min Act: -0.0000

Data Index: 547659 (C4 (Web Text))

Max Activating Token Index: 666

Text #4

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6569. Min Act: -0.0000

Data Index: 689422 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6331. Min Act: -0.0000

Data Index: 1123394 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6143. Min Act: -0.0000

Data Index: 1064686 (C4 (Web Text))

Max Activating Token Index: 998

Text #7

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6069. Min Act: -0.0000

Data Index: 714139 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1054282 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6178. Min Act: -0.0000

Data Index: 250525 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5613. Min Act: -0.0000

Data Index: 972299 (C4 (Web Text))

Max Activating Token Index: 365

Text #11

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.6068. Min Act: -0.0000

Data Index: 23959 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5838. Min Act: -0.0000

Data Index: 60783 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1086733 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5758. Min Act: -0.0000

Data Index: 818594 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5732. Min Act: -0.0000

Data Index: 848644 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5911. Min Act: -0.0000

Data Index: 846706 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5622. Min Act: -0.0000

Data Index: 774551 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1020335 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 0.8681. Min Range: -0.8681

Max Act: 0.5470. Min Act: -0.0000

Data Index: 118488 (C4 (Web Text))

Max Activating Token Index: 231