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

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

Neuron 3776 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9206. Min Act: -0.0000

Data Index: 1198643 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8310. Min Act: -0.0000

Data Index: 388039 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8576. Min Act: -0.0000

Data Index: 334325 (C4 (Web Text))

Max Activating Token Index: 756

Text #3

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.9530. Min Act: -0.0000

Data Index: 633904 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8014. Min Act: -0.0000

Data Index: 342359 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.8903. Min Act: -0.0000

Data Index: 280858 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.5929. Min Act: -0.0000

Data Index: 837409 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7540. Min Act: -0.0000

Data Index: 1313096 (C4 (Web Text))

Max Activating Token Index: 744

Text #8

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6586. Min Act: -0.0000

Data Index: 1265614 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6454. Min Act: -0.0000

Data Index: 176510 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7305. Min Act: -0.0000

Data Index: 894614 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7070. Min Act: -0.0000

Data Index: 1234491 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7061. Min Act: -0.0000

Data Index: 680788 (C4 (Web Text))

Max Activating Token Index: 463

Text #13

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7069. Min Act: -0.0000

Data Index: 579183 (C4 (Web Text))

Max Activating Token Index: 958

Text #14

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.7041. Min Act: -0.0000

Data Index: 954063 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6753. Min Act: -0.0000

Data Index: 81591 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.5755. Min Act: -0.0000

Data Index: 1187997 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6704. Min Act: -0.0000

Data Index: 1264197 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6622. Min Act: -0.0000

Data Index: 1210694 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.9530. Min Range: -1.9530

Max Act: 1.6480. Min Act: -0.0000

Data Index: 308319 (C4 (Web Text))

Max Activating Token Index: 769