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

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

Neuron 1464 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.5028. Min Act: -0.0000

Data Index: 553781 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.4675. Min Act: -0.0000

Data Index: 203459 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1277018 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.4623. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3993. Min Act: -0.0000

Data Index: 335995 (C4 (Web Text))

Max Activating Token Index: 355

Text #5

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3784. Min Act: -0.0000

Data Index: 1276744 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.4051. Min Act: -0.0000

Data Index: 1246319 (C4 (Web Text))

Max Activating Token Index: 653

Text #7

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3495. Min Act: -0.0000

Data Index: 789095 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1188969 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3643. Min Act: -0.0000

Data Index: 473607 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3762. Min Act: -0.0000

Data Index: 121972 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3744. Min Act: -0.0000

Data Index: 213161 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3277. Min Act: -0.0000

Data Index: 929680 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1227564 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3417. Min Act: -0.0000

Data Index: 631430 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3362. Min Act: -0.0000

Data Index: 1310802 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3590. Min Act: -0.0000

Data Index: 287647 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3251. Min Act: -0.0000

Data Index: 1048250 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1089075 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.5028. Min Range: -0.5028

Max Act: 0.3575. Min Act: -0.0000

Data Index: 1015330 (C4 (Web Text))

Max Activating Token Index: 579