Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1957 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1067. Min Act: -0.0001

Data Index: 1368298 (Python Code)

Max Activating Token Index: 850

Text #1

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.1159. Min Act: -0.0001

Data Index: 973437 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0755. Min Act: -0.0001

Data Index: 660402 (C4 (Web Text))

Max Activating Token Index: 978

Text #3

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0756. Min Act: -0.0001

Data Index: 245535 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0735. Min Act: -0.0000

Data Index: 1291697 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0708. Min Act: -0.0001

Data Index: 178472 (C4 (Web Text))

Max Activating Token Index: 68

Text #6

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0734. Min Act: -0.0001

Data Index: 640928 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0726. Min Act: -0.0001

Data Index: 321244 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0776. Min Act: -0.0001

Data Index: 850710 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0614. Min Act: -0.0001

Data Index: 685858 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1236437 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0700. Min Act: -0.0001

Data Index: 39394 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0605. Min Act: -0.0001

Data Index: 941364 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1257960 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1297110 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0612. Min Act: -0.0001

Data Index: 1301033 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0626. Min Act: -0.0001

Data Index: 449845 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0596. Min Act: -0.0000

Data Index: 683369 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0510. Min Act: -0.0001

Data Index: 667064 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.1159. Min Range: -0.1159

Max Act: 0.0613. Min Act: -0.0001

Data Index: 821853 (C4 (Web Text))

Max Activating Token Index: 851