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

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

Neuron 1010 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: 1.4096. Min Range: -1.4096

Max Act: 1.4096. Min Act: -0.0001

Data Index: 909430 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.3353. Min Act: -0.0001

Data Index: 339145 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2876. Min Act: -0.0001

Data Index: 1011526 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2037. Min Act: -0.0001

Data Index: 61947 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.3094. Min Act: -0.0001

Data Index: 1320363 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2825. Min Act: -0.0001

Data Index: 850816 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1718. Min Act: -0.0001

Data Index: 299869 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.2261. Min Act: -0.0001

Data Index: 898612 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1690. Min Act: -0.0001

Data Index: 116665 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1392. Min Act: -0.0001

Data Index: 759594 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1196. Min Act: -0.0001

Data Index: 59379 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0849. Min Act: -0.0001

Data Index: 489918 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0225. Min Act: -0.0001

Data Index: 997402 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0783. Min Act: -0.0001

Data Index: 78521 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.1005. Min Act: -0.0001

Data Index: 644242 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9989. Min Act: -0.0001

Data Index: 191470 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0633. Min Act: -0.0001

Data Index: 1339206 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0308. Min Act: -0.0001

Data Index: 723058 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 1.4096. Min Range: -1.4096

Max Act: 0.9874. Min Act: -0.0001

Data Index: 230325 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 1.4096. Min Range: -1.4096

Max Act: 1.0567. Min Act: -0.0001

Data Index: 984807 (C4 (Web Text))

Max Activating Token Index: 728