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

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

Neuron 3557 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: 0.4572. Min Range: -0.4572

Max Act: 0.4339. Min Act: -0.0000

Data Index: 93483 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4572. Min Act: -0.0000

Data Index: 64440 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1293514 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4299. Min Act: -0.0000

Data Index: 728069 (C4 (Web Text))

Max Activating Token Index: 649

Text #4

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4143. Min Act: -0.0000

Data Index: 517205 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4126. Min Act: -0.0000

Data Index: 685136 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3965. Min Act: -0.0000

Data Index: 599432 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4108. Min Act: -0.0000

Data Index: 121412 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3803. Min Act: -0.0000

Data Index: 816553 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3808. Min Act: -0.0000

Data Index: 774826 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3986. Min Act: -0.0000

Data Index: 945859 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3864. Min Act: -0.0000

Data Index: 576117 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.4093. Min Act: -0.0000

Data Index: 928425 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3722. Min Act: -0.0000

Data Index: 954435 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3954. Min Act: -0.0000

Data Index: 1279617 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1285810 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3793. Min Act: -0.0000

Data Index: 839314 (C4 (Web Text))

Max Activating Token Index: 69

Text #17

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1266019 (C4 (Web Text))

Max Activating Token Index: 582

Text #18

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3648. Min Act: -0.0000

Data Index: 931988 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.4572. Min Range: -0.4572

Max Act: 0.3858. Min Act: -0.0000

Data Index: 999203 (C4 (Web Text))

Max Activating Token Index: 997