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

Dataset: The Pile

Neuron 3382 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: 0.6541. Min Range: -0.6541

Max Act: 0.6541. Min Act: -0.0000

Data Index: 801907 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6445. Min Act: -0.0000

Data Index: 1491379 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1428904 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.6014. Min Act: -0.0000

Data Index: 686980 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5803. Min Act: -0.0000

Data Index: 446298 (The Pile)

Max Activating Token Index: 469

Text #5

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5973. Min Act: -0.0000

Data Index: 1246260 (The Pile)

Max Activating Token Index: 794

Text #6

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5978. Min Act: -0.0000

Data Index: 683428 (The Pile)

Max Activating Token Index: 885

Text #7

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1548246 (The Pile)

Max Activating Token Index: 431

Text #8

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1081698 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1880971 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1984444 (The Pile)

Max Activating Token Index: 365

Text #11

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5425. Min Act: -0.0000

Data Index: 751981 (The Pile)

Max Activating Token Index: 354

Text #12

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5312. Min Act: -0.0000

Data Index: 229665 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1182189 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5495. Min Act: -0.0000

Data Index: 725489 (The Pile)

Max Activating Token Index: 155

Text #15

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.4955. Min Act: -0.0000

Data Index: 224460 (The Pile)

Max Activating Token Index: 722

Text #16

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5493. Min Act: -0.0000

Data Index: 23636 (The Pile)

Max Activating Token Index: 471

Text #17

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5004. Min Act: -0.0000

Data Index: 1313088 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1865848 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.6541. Min Range: -0.6541

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1775123 (The Pile)

Max Activating Token Index: 253