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

Dataset: The Pile

Neuron 3477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.9538. Min Act: -0.0000

Data Index: 608435 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.6184. Min Act: -0.0000

Data Index: 1406472 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.1114. Min Act: -0.0000

Data Index: 1251646 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.2543. Min Act: -0.0000

Data Index: 745813 (The Pile)

Max Activating Token Index: 738

Text #4

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.1220. Min Act: -0.0000

Data Index: 954794 (The Pile)

Max Activating Token Index: 490

Text #5

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.0734. Min Act: -0.0000

Data Index: 1881111 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.1307. Min Act: -0.0000

Data Index: 127695 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.0776. Min Act: -0.0000

Data Index: 1533186 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.0518. Min Act: -0.0000

Data Index: 988848 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.1843. Min Act: -0.0000

Data Index: 279841 (The Pile)

Max Activating Token Index: 79

Text #10

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.9929. Min Act: -0.0000

Data Index: 1324388 (The Pile)

Max Activating Token Index: 904

Text #11

Max Range: 3.9538. Min Range: -3.9538

Max Act: 3.0601. Min Act: -0.0000

Data Index: 524848 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.6327. Min Act: -0.0000

Data Index: 1967656 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.8755. Min Act: -0.0000

Data Index: 76355 (The Pile)

Max Activating Token Index: 444

Text #14

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.8747. Min Act: -0.0000

Data Index: 1942759 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.8420. Min Act: -0.0000

Data Index: 337004 (The Pile)

Max Activating Token Index: 285

Text #16

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.9525. Min Act: -0.0000

Data Index: 1452559 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.7928. Min Act: -0.0000

Data Index: 248213 (The Pile)

Max Activating Token Index: 343

Text #18

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.5023. Min Act: -0.0000

Data Index: 653777 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 3.9538. Min Range: -3.9538

Max Act: 2.7424. Min Act: -0.0000

Data Index: 1394273 (The Pile)

Max Activating Token Index: 916