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

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

Neuron 2330 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: 2.4444. Min Range: -2.4444

Max Act: 2.4444. Min Act: -0.0000

Data Index: 679333 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.1046. Min Act: -0.0000

Data Index: 295465 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.9833. Min Act: -0.0000

Data Index: 311279 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.7575. Min Act: -0.0000

Data Index: 1061720 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 2.4444. Min Range: -2.4444

Max Act: 2.0560. Min Act: -0.0000

Data Index: 561967 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.6866. Min Act: -0.0000

Data Index: 1113485 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.5887. Min Act: -0.0000

Data Index: 1286003 (C4 (Web Text))

Max Activating Token Index: 373

Text #7

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4911. Min Act: -0.0000

Data Index: 980761 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.5636. Min Act: -0.0000

Data Index: 724114 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4497. Min Act: -0.0000

Data Index: 431594 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4363. Min Act: -0.0000

Data Index: 602703 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4286. Min Act: -0.0000

Data Index: 473319 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.5121. Min Act: -0.0000

Data Index: 1220165 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4191. Min Act: -0.0000

Data Index: 385995 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.3377. Min Act: -0.0000

Data Index: 902295 (C4 (Web Text))

Max Activating Token Index: 627

Text #15

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4967. Min Act: -0.0000

Data Index: 1222666 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4640. Min Act: -0.0000

Data Index: 141197 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.6433. Min Act: -0.0000

Data Index: 963016 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.5305. Min Act: -0.0000

Data Index: 884689 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 2.4444. Min Range: -2.4444

Max Act: 1.4353. Min Act: -0.0000

Data Index: 472519 (C4 (Web Text))

Max Activating Token Index: 928