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

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

Neuron 3344 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8563. Min Act: -0.0000

Data Index: 43236 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.8475. Min Act: -0.0000

Data Index: 411613 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7288. Min Act: -0.0000

Data Index: 99073 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7449. Min Act: -0.0000

Data Index: 783469 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6879. Min Act: -0.0000

Data Index: 96833 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7381. Min Act: -0.0000

Data Index: 322325 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.7071. Min Act: -0.0000

Data Index: 742298 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6887. Min Act: -0.0000

Data Index: 134066 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6993. Min Act: -0.0000

Data Index: 997934 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6961. Min Act: -0.0000

Data Index: 918536 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6768. Min Act: -0.0000

Data Index: 642344 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6724. Min Act: -0.0000

Data Index: 128658 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6724. Min Act: -0.0000

Data Index: 532729 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1126587 (C4 (Web Text))

Max Activating Token Index: 422

Text #14

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1049926 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6651. Min Act: -0.0000

Data Index: 81314 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6490. Min Act: -0.0000

Data Index: 913666 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6709. Min Act: -0.0000

Data Index: 263452 (C4 (Web Text))

Max Activating Token Index: 285

Text #18

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6405. Min Act: -0.0000

Data Index: 128857 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 0.8563. Min Range: -0.8563

Max Act: 0.6256. Min Act: -0.0000

Data Index: 787044 (C4 (Web Text))

Max Activating Token Index: 812