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

Dataset: The Pile

Neuron 2170 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.8377. Min Act: -0.0000

Data Index: 667348 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1300499 (The Pile)

Max Activating Token Index: 430

Text #2

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6083. Min Act: -0.0000

Data Index: 529829 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1744641 (The Pile)

Max Activating Token Index: 379

Text #4

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6171. Min Act: -0.0000

Data Index: 117539 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6173. Min Act: -0.0000

Data Index: 616497 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6511. Min Act: -0.0000

Data Index: 286400 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6001. Min Act: -0.0000

Data Index: 14620 (The Pile)

Max Activating Token Index: 759

Text #8

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5983. Min Act: -0.0000

Data Index: 910124 (The Pile)

Max Activating Token Index: 629

Text #9

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1085605 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1833674 (The Pile)

Max Activating Token Index: 572

Text #11

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5725. Min Act: -0.0000

Data Index: 651653 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4709. Min Act: -0.0000

Data Index: 617445 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1237097 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5621. Min Act: -0.0000

Data Index: 8027 (The Pile)

Max Activating Token Index: 438

Text #15

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1314430 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1745707 (The Pile)

Max Activating Token Index: 628

Text #17

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5254. Min Act: -0.0000

Data Index: 1683844 (The Pile)

Max Activating Token Index: 813

Text #18

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.5335. Min Act: -0.0000

Data Index: 129200 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 0.8377. Min Range: -0.8377

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1199409 (The Pile)

Max Activating Token Index: 377