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

Dataset: The Pile

Neuron 1402 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: 1.0000. Min Range: -1.0000

Max Act: 1.0000. Min Act: -0.0000

Data Index: 416118 (The Pile)

Max Activating Token Index: 673

Text #1

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9957. Min Act: -0.0000

Data Index: 438724 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1069533 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1359113 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1771759 (The Pile)

Max Activating Token Index: 526

Text #5

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8390. Min Act: -0.0000

Data Index: 1891458 (The Pile)

Max Activating Token Index: 630

Text #6

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8168. Min Act: -0.0000

Data Index: 137279 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8572. Min Act: -0.0000

Data Index: 339030 (The Pile)

Max Activating Token Index: 481

Text #8

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7794. Min Act: -0.0000

Data Index: 762687 (The Pile)

Max Activating Token Index: 411

Text #9

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7885. Min Act: -0.0000

Data Index: 1274387 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7288. Min Act: -0.0000

Data Index: 1094018 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6772. Min Act: -0.0000

Data Index: 135347 (The Pile)

Max Activating Token Index: 830

Text #12

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1078164 (The Pile)

Max Activating Token Index: 97

Text #13

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7311. Min Act: -0.0000

Data Index: 1680698 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7341. Min Act: -0.0000

Data Index: 1341012 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7235. Min Act: -0.0000

Data Index: 15244 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1989341 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6567. Min Act: -0.0000

Data Index: 152554 (The Pile)

Max Activating Token Index: 199

Text #18

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6734. Min Act: -0.0000

Data Index: 517139 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6671. Min Act: -0.0000

Data Index: 1206168 (The Pile)

Max Activating Token Index: 342