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

Dataset: The Pile

Neuron 1513 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1597781 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8711. Min Act: -0.0000

Data Index: 290393 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1811701 (The Pile)

Max Activating Token Index: 521

Text #3

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.6717. Min Act: -0.0000

Data Index: 917828 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1372305 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7589. Min Act: -0.0000

Data Index: 557292 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7935. Min Act: -0.0000

Data Index: 164788 (The Pile)

Max Activating Token Index: 260

Text #7

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7799. Min Act: -0.0000

Data Index: 1528326 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7534. Min Act: -0.0000

Data Index: 1700057 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7570. Min Act: -0.0000

Data Index: 979222 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7061. Min Act: -0.0000

Data Index: 75421 (The Pile)

Max Activating Token Index: 719

Text #11

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7480. Min Act: -0.0000

Data Index: 530672 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7755. Min Act: -0.0000

Data Index: 431464 (The Pile)

Max Activating Token Index: 458

Text #13

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7880. Min Act: -0.0000

Data Index: 824762 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7859. Min Act: -0.0000

Data Index: 596797 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7786. Min Act: -0.0000

Data Index: 169814 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7908. Min Act: -0.0000

Data Index: 649980 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7605. Min Act: -0.0000

Data Index: 1012677 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1807885 (The Pile)

Max Activating Token Index: 1008

Text #19

Max Range: 0.9941. Min Range: -0.9941

Max Act: 0.6676. Min Act: -0.0000

Data Index: 492309 (The Pile)

Max Activating Token Index: 771