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

Dataset: The Pile

Neuron 2591 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: 1.0268. Min Range: -1.0268

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1560261 (The Pile)

Max Activating Token Index: 293

Text #1

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.9231. Min Act: -0.0000

Data Index: 632935 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.9675. Min Act: -0.0000

Data Index: 24144 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8990. Min Act: -0.0000

Data Index: 1212613 (The Pile)

Max Activating Token Index: 231

Text #4

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.9008. Min Act: -0.0000

Data Index: 1887178 (The Pile)

Max Activating Token Index: 356

Text #5

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8959. Min Act: -0.0000

Data Index: 436258 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8521. Min Act: -0.0000

Data Index: 895497 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8664. Min Act: -0.0000

Data Index: 986186 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1724695 (The Pile)

Max Activating Token Index: 454

Text #9

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1519529 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8366. Min Act: -0.0000

Data Index: 86064 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8225. Min Act: -0.0000

Data Index: 1067402 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7588. Min Act: -0.0000

Data Index: 988943 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8061. Min Act: -0.0000

Data Index: 1829938 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8020. Min Act: -0.0000

Data Index: 149391 (The Pile)

Max Activating Token Index: 417

Text #15

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1458092 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1024486 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.8264. Min Act: -0.0000

Data Index: 63818 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7167. Min Act: -0.0000

Data Index: 1213760 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.0268. Min Range: -1.0268

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1496513 (The Pile)

Max Activating Token Index: 77