Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3552 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1073291 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5387. Min Act: -0.0001

Data Index: 837787 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5191. Min Act: -0.0000

Data Index: 710082 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5368. Min Act: -0.0001

Data Index: 248822 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.5062. Min Act: -0.0001

Data Index: 754615 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4828. Min Act: -0.0001

Data Index: 184486 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4585. Min Act: -0.0001

Data Index: 369107 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4909. Min Act: -0.0000

Data Index: 720011 (C4 (Web Text))

Max Activating Token Index: 657

Text #8

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4729. Min Act: -0.0001

Data Index: 76902 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4704. Min Act: -0.0000

Data Index: 309382 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4345. Min Act: -0.0000

Data Index: 14741 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4540. Min Act: -0.0001

Data Index: 609963 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4409. Min Act: -0.0001

Data Index: 81799 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4402. Min Act: -0.0000

Data Index: 789283 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4209. Min Act: -0.0000

Data Index: 351246 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4035. Min Act: -0.0001

Data Index: 540889 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4128. Min Act: -0.0001

Data Index: 1246664 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4014. Min Act: -0.0001

Data Index: 1090246 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1147451 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.5553. Min Range: -0.5553

Max Act: 0.4060. Min Act: -0.0000

Data Index: 887557 (C4 (Web Text))

Max Activating Token Index: 186