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

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

Neuron 3781 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.6925. Min Act: -0.0000

Data Index: 222646 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.2931. Min Act: -0.0000

Data Index: 965328 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.2659. Min Act: -0.0000

Data Index: 460544 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1872. Min Act: -0.0000

Data Index: 46851 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1802. Min Act: -0.0000

Data Index: 245133 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1313. Min Act: -0.0000

Data Index: 1221555 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1241. Min Act: -0.0000

Data Index: 199618 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1115026 (C4 (Web Text))

Max Activating Token Index: 422

Text #8

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1207. Min Act: -0.0000

Data Index: 1049088 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1640. Min Act: -0.0000

Data Index: 945070 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1588. Min Act: -0.0000

Data Index: 286252 (C4 (Web Text))

Max Activating Token Index: 950

Text #11

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.0015. Min Act: -0.0000

Data Index: 426203 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.0908. Min Act: -0.0000

Data Index: 32454 (C4 (Web Text))

Max Activating Token Index: 241

Text #13

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.0616. Min Act: -0.0000

Data Index: 774602 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.1175. Min Act: -0.0000

Data Index: 1267201 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.0626. Min Act: -0.0000

Data Index: 79556 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.0692. Min Act: -0.0000

Data Index: 704872 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.6925. Min Range: -1.6925

Max Act: 1.0058. Min Act: -0.0000

Data Index: 181768 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.6925. Min Range: -1.6925

Max Act: 0.9911. Min Act: -0.0000

Data Index: 168642 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.6925. Min Range: -1.6925

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1069825 (C4 (Web Text))

Max Activating Token Index: 340