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

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

Neuron 3733 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5311. Min Act: -0.0000

Data Index: 159335 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1186936 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5286. Min Act: -0.0000

Data Index: 379179 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1357254 (C4 (Web Text))

Max Activating Token Index: 487

Text #4

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5075. Min Act: -0.0000

Data Index: 74744 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1334084 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4983. Min Act: -0.0000

Data Index: 925334 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4813. Min Act: -0.0000

Data Index: 292499 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4925. Min Act: -0.0000

Data Index: 395878 (C4 (Web Text))

Max Activating Token Index: 841

Text #9

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4913. Min Act: -0.0000

Data Index: 116828 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.5069. Min Act: -0.0000

Data Index: 535878 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4908. Min Act: -0.0000

Data Index: 775312 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1349104 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4733. Min Act: -0.0000

Data Index: 507666 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4672. Min Act: -0.0000

Data Index: 991027 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4495. Min Act: -0.0000

Data Index: 408745 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4024. Min Act: -0.0000

Data Index: 521923 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4568. Min Act: -0.0000

Data Index: 939719 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4539. Min Act: -0.0000

Data Index: 133627 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.5506. Min Range: -0.5506

Max Act: 0.4443. Min Act: -0.0000

Data Index: 602395 (C4 (Web Text))

Max Activating Token Index: 449