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

Dataset: The Pile

Neuron 1740 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8740. Min Act: -0.0000

Data Index: 546296 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1684261 (The Pile)

Max Activating Token Index: 634

Text #2

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1452149 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1077605 (The Pile)

Max Activating Token Index: 753

Text #4

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1124999 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7678. Min Act: -0.0000

Data Index: 414215 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6709. Min Act: -0.0000

Data Index: 695563 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1381480 (The Pile)

Max Activating Token Index: 1013

Text #8

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6547. Min Act: -0.0000

Data Index: 833793 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.7119. Min Act: -0.0000

Data Index: 1840215 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6905. Min Act: -0.0000

Data Index: 97147 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6936. Min Act: -0.0000

Data Index: 1071230 (The Pile)

Max Activating Token Index: 585

Text #12

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6881. Min Act: -0.0000

Data Index: 310094 (The Pile)

Max Activating Token Index: 255

Text #13

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6612. Min Act: -0.0000

Data Index: 556909 (The Pile)

Max Activating Token Index: 472

Text #14

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6778. Min Act: -0.0000

Data Index: 1494706 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6367. Min Act: -0.0000

Data Index: 719693 (The Pile)

Max Activating Token Index: 559

Text #16

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6326. Min Act: -0.0000

Data Index: 514352 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6369. Min Act: -0.0000

Data Index: 466796 (The Pile)

Max Activating Token Index: 959

Text #18

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.6468. Min Act: -0.0000

Data Index: 878729 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.8740. Min Range: -0.8740

Max Act: 0.5941. Min Act: -0.0000

Data Index: 1767151 (The Pile)

Max Activating Token Index: 142