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

Dataset: The Pile

Neuron 2134 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: 1.1052. Min Range: -1.1052

Max Act: 1.1052. Min Act: -0.0000

Data Index: 192889 (The Pile)

Max Activating Token Index: 255

Text #1

Max Range: 1.1052. Min Range: -1.1052

Max Act: 1.0231. Min Act: -0.0000

Data Index: 621662 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.9215. Min Act: -0.0000

Data Index: 1792176 (The Pile)

Max Activating Token Index: 613

Text #3

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8468. Min Act: -0.0000

Data Index: 1592200 (The Pile)

Max Activating Token Index: 927

Text #4

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.7926. Min Act: -0.0000

Data Index: 653160 (The Pile)

Max Activating Token Index: 231

Text #5

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6992. Min Act: -0.0000

Data Index: 128787 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1829670 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.7331. Min Act: -0.0000

Data Index: 210828 (The Pile)

Max Activating Token Index: 23

Text #8

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6784. Min Act: -0.0000

Data Index: 445220 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.7377. Min Act: -0.0000

Data Index: 585563 (The Pile)

Max Activating Token Index: 562

Text #10

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.7313. Min Act: -0.0000

Data Index: 257333 (The Pile)

Max Activating Token Index: 262

Text #11

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6488. Min Act: -0.0000

Data Index: 585287 (The Pile)

Max Activating Token Index: 945

Text #12

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1072844 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6849. Min Act: -0.0000

Data Index: 501770 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6500. Min Act: -0.0000

Data Index: 143591 (The Pile)

Max Activating Token Index: 835

Text #15

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6701. Min Act: -0.0000

Data Index: 924213 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1621614 (The Pile)

Max Activating Token Index: 463

Text #17

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6651. Min Act: -0.0000

Data Index: 1773672 (The Pile)

Max Activating Token Index: 735

Text #18

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1850531 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 1.1052. Min Range: -1.1052

Max Act: 0.6657. Min Act: -0.0000

Data Index: 584531 (The Pile)

Max Activating Token Index: 439