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

Dataset: The Pile

Neuron 2574 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6374. Min Range: -1.6374

Max Act: 1.6374. Min Act: -0.0000

Data Index: 516426 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 1.6374. Min Range: -1.6374

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1466921 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 1.6374. Min Range: -1.6374

Max Act: 1.0985. Min Act: -0.0000

Data Index: 454397 (The Pile)

Max Activating Token Index: 92

Text #3

Max Range: 1.6374. Min Range: -1.6374

Max Act: 1.1648. Min Act: -0.0000

Data Index: 872192 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 1.6374. Min Range: -1.6374

Max Act: 1.0202. Min Act: -0.0000

Data Index: 1260441 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1451713 (The Pile)

Max Activating Token Index: 97

Text #6

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1329956 (The Pile)

Max Activating Token Index: 821

Text #7

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1712313 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9231. Min Act: -0.0000

Data Index: 765461 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9056. Min Act: -0.0000

Data Index: 1449508 (The Pile)

Max Activating Token Index: 461

Text #10

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.7431. Min Act: -0.0000

Data Index: 1526339 (The Pile)

Max Activating Token Index: 939

Text #11

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1222958 (The Pile)

Max Activating Token Index: 282

Text #12

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9814. Min Act: -0.0000

Data Index: 178773 (The Pile)

Max Activating Token Index: 85

Text #13

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.8605. Min Act: -0.0000

Data Index: 918988 (The Pile)

Max Activating Token Index: 544

Text #14

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.9503. Min Act: -0.0000

Data Index: 879760 (The Pile)

Max Activating Token Index: 403

Text #15

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1748035 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.8357. Min Act: -0.0000

Data Index: 624733 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.8310. Min Act: -0.0000

Data Index: 387397 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.8253. Min Act: -0.0000

Data Index: 466060 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 1.6374. Min Range: -1.6374

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1024213 (The Pile)

Max Activating Token Index: 408