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

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

Neuron 1639 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.2882. Min Act: -0.0000

Data Index: 131049 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1297740 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.2791. Min Act: -0.0000

Data Index: 413136 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.2698. Min Act: -0.0000

Data Index: 111110 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1763. Min Act: -0.0000

Data Index: 407197 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1339. Min Act: -0.0000

Data Index: 329586 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1012445 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0801. Min Act: -0.0000

Data Index: 790616 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0794. Min Act: -0.0000

Data Index: 455693 (C4 (Web Text))

Max Activating Token Index: 874

Text #9

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0623. Min Act: -0.0000

Data Index: 42228 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.1184. Min Act: -0.0000

Data Index: 1195708 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9861. Min Act: -0.0000

Data Index: 654611 (C4 (Web Text))

Max Activating Token Index: 437

Text #12

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0227. Min Act: -0.0000

Data Index: 562423 (C4 (Web Text))

Max Activating Token Index: 625

Text #13

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0217. Min Act: -0.0000

Data Index: 473355 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9905. Min Act: -0.0000

Data Index: 1080576 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9857. Min Act: -0.0000

Data Index: 931198 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9380. Min Act: -0.0000

Data Index: 438032 (C4 (Web Text))

Max Activating Token Index: 1017

Text #17

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9488. Min Act: -0.0000

Data Index: 36351 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 1.2882. Min Range: -1.2882

Max Act: 0.9513. Min Act: -0.0000

Data Index: 830092 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 1.2882. Min Range: -1.2882

Max Act: 1.0020. Min Act: -0.0000

Data Index: 249264 (C4 (Web Text))

Max Activating Token Index: 894