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

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

Neuron 4431 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6731. Min Act: -0.0000

Data Index: 128796 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5843. Min Act: -0.0000

Data Index: 843785 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5919. Min Act: -0.0000

Data Index: 1165279 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5249. Min Act: -0.0000

Data Index: 6837 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1064432 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5339. Min Act: -0.0000

Data Index: 966185 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5313. Min Act: -0.0000

Data Index: 791137 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1102158 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4863. Min Act: -0.0000

Data Index: 224232 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4945. Min Act: -0.0000

Data Index: 19516 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4834. Min Act: -0.0000

Data Index: 481538 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4794. Min Act: -0.0000

Data Index: 954666 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1345472 (C4 (Web Text))

Max Activating Token Index: 276

Text #13

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4904. Min Act: -0.0000

Data Index: 916685 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4830. Min Act: -0.0000

Data Index: 389353 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4665. Min Act: -0.0000

Data Index: 916448 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4731. Min Act: -0.0000

Data Index: 663239 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1077954 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4529. Min Act: -0.0000

Data Index: 722155 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4680. Min Act: -0.0000

Data Index: 1286825 (C4 (Web Text))

Max Activating Token Index: 493