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

Dataset: The Pile

Neuron 4151 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2702. Min Range: -4.2702

Max Act: 4.2702. Min Act: -0.0000

Data Index: 465077 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.5872. Min Act: -0.0000

Data Index: 1722436 (The Pile)

Max Activating Token Index: 448

Text #2

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.5088. Min Act: -0.0000

Data Index: 449212 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.4545. Min Act: -0.0000

Data Index: 167085 (The Pile)

Max Activating Token Index: 316

Text #4

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.5805. Min Act: -0.0000

Data Index: 262455 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.3082. Min Act: -0.0000

Data Index: 823111 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.3669. Min Act: -0.0000

Data Index: 1246377 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.2643. Min Act: -0.0000

Data Index: 1441129 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.4312. Min Act: -0.0000

Data Index: 735085 (The Pile)

Max Activating Token Index: 341

Text #9

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.2413. Min Act: -0.0000

Data Index: 145895 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.2549. Min Act: -0.0000

Data Index: 869097 (The Pile)

Max Activating Token Index: 956

Text #11

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.2140. Min Act: -0.0000

Data Index: 130337 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.2259. Min Act: -0.0000

Data Index: 680311 (The Pile)

Max Activating Token Index: 562

Text #13

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.3522. Min Act: -0.0000

Data Index: 1660258 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 4.2702. Min Range: -4.2702

Max Act: 2.6671. Min Act: -0.0000

Data Index: 1119891 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.0812. Min Act: -0.0000

Data Index: 223022 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.0219. Min Act: -0.0000

Data Index: 1182496 (The Pile)

Max Activating Token Index: 527

Text #17

Max Range: 4.2702. Min Range: -4.2702

Max Act: 2.9525. Min Act: -0.0000

Data Index: 175099 (The Pile)

Max Activating Token Index: 995

Text #18

Max Range: 4.2702. Min Range: -4.2702

Max Act: 3.3043. Min Act: -0.0000

Data Index: 236591 (The Pile)

Max Activating Token Index: 525

Text #19

Max Range: 4.2702. Min Range: -4.2702

Max Act: 2.7859. Min Act: -0.0000

Data Index: 746285 (The Pile)

Max Activating Token Index: 980