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

Dataset: The Pile

Neuron 317 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1203962 (The Pile)

Max Activating Token Index: 756

Text #1

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4549. Min Act: -0.0000

Data Index: 1193482 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1168449 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4141. Min Act: -0.0000

Data Index: 1048851 (The Pile)

Max Activating Token Index: 417

Text #4

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3828. Min Act: -0.0000

Data Index: 12873 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.4571. Min Act: -0.0000

Data Index: 916834 (The Pile)

Max Activating Token Index: 903

Text #6

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3638. Min Act: -0.0000

Data Index: 704838 (The Pile)

Max Activating Token Index: 255

Text #7

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3320. Min Act: -0.0000

Data Index: 649407 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1226633 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1022169 (The Pile)

Max Activating Token Index: 269

Text #10

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1990234 (The Pile)

Max Activating Token Index: 694

Text #11

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3796. Min Act: -0.0000

Data Index: 790917 (The Pile)

Max Activating Token Index: 469

Text #12

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3526. Min Act: -0.0000

Data Index: 112204 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3660. Min Act: -0.0000

Data Index: 93082 (The Pile)

Max Activating Token Index: 282

Text #14

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3232. Min Act: -0.0000

Data Index: 1985265 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3836. Min Act: -0.0000

Data Index: 459714 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3197. Min Act: -0.0000

Data Index: 1191887 (The Pile)

Max Activating Token Index: 639

Text #17

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1128788 (The Pile)

Max Activating Token Index: 609

Text #18

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3971. Min Act: -0.0000

Data Index: 966865 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.5179. Min Range: -0.5179

Max Act: 0.3524. Min Act: -0.0000

Data Index: 309042 (The Pile)

Max Activating Token Index: 301