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

Dataset: The Pile

Neuron 1975 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6997. Min Act: -0.0000

Data Index: 43873 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.6490. Min Act: -0.0000

Data Index: 1913054 (The Pile)

Max Activating Token Index: 672

Text #2

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1464763 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4861. Min Act: -0.0000

Data Index: 1041486 (The Pile)

Max Activating Token Index: 772

Text #4

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5445. Min Act: -0.0000

Data Index: 928447 (The Pile)

Max Activating Token Index: 158

Text #5

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.5159. Min Act: -0.0000

Data Index: 461571 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1382544 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4463. Min Act: -0.0000

Data Index: 788409 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4773. Min Act: -0.0000

Data Index: 1454842 (The Pile)

Max Activating Token Index: 792

Text #9

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4417. Min Act: -0.0000

Data Index: 1435123 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4150. Min Act: -0.0000

Data Index: 47310 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4437. Min Act: -0.0000

Data Index: 931456 (The Pile)

Max Activating Token Index: 187

Text #12

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4259. Min Act: -0.0000

Data Index: 416266 (The Pile)

Max Activating Token Index: 319

Text #13

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1154064 (The Pile)

Max Activating Token Index: 609

Text #14

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1533270 (The Pile)

Max Activating Token Index: 256

Text #15

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4515. Min Act: -0.0000

Data Index: 806894 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1146099 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4332. Min Act: -0.0000

Data Index: 1488028 (The Pile)

Max Activating Token Index: 137

Text #18

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.4307. Min Act: -0.0000

Data Index: 316169 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 0.6997. Min Range: -0.6997

Max Act: 0.3955. Min Act: -0.0000

Data Index: 741558 (The Pile)

Max Activating Token Index: 188