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

Dataset: The Pile

Neuron 995 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: 0.5430. Min Range: -0.5430

Max Act: 0.5430. Min Act: -0.0000

Data Index: 305513 (The Pile)

Max Activating Token Index: 854

Text #1

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5223. Min Act: -0.0000

Data Index: 189458 (The Pile)

Max Activating Token Index: 173

Text #2

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1399014 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4825. Min Act: -0.0000

Data Index: 672789 (The Pile)

Max Activating Token Index: 228

Text #4

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1202752 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4924. Min Act: -0.0000

Data Index: 44029 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4670. Min Act: -0.0000

Data Index: 952328 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4830. Min Act: -0.0000

Data Index: 601508 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1160362 (The Pile)

Max Activating Token Index: 684

Text #9

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1708683 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4588. Min Act: -0.0000

Data Index: 591640 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1388933 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4708. Min Act: -0.0000

Data Index: 87513 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4842. Min Act: -0.0000

Data Index: 187229 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1114441 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4512. Min Act: -0.0000

Data Index: 509945 (The Pile)

Max Activating Token Index: 355

Text #16

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1431602 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1326030 (The Pile)

Max Activating Token Index: 130

Text #18

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4774. Min Act: -0.0000

Data Index: 13066 (The Pile)

Max Activating Token Index: 761

Text #19

Max Range: 0.5430. Min Range: -0.5430

Max Act: 0.4574. Min Act: -0.0000

Data Index: 718171 (The Pile)

Max Activating Token Index: 81