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

Dataset: The Pile

Neuron 3498 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1666576 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2738. Min Act: -0.0000

Data Index: 1762394 (The Pile)

Max Activating Token Index: 797

Text #2

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2865. Min Act: -0.0000

Data Index: 616749 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2431. Min Act: -0.0000

Data Index: 896751 (The Pile)

Max Activating Token Index: 554

Text #4

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2647. Min Act: -0.0000

Data Index: 1280671 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2778. Min Act: -0.0000

Data Index: 447058 (The Pile)

Max Activating Token Index: 239

Text #6

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1606101 (The Pile)

Max Activating Token Index: 670

Text #7

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2695. Min Act: -0.0000

Data Index: 644683 (The Pile)

Max Activating Token Index: 460

Text #8

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2807. Min Act: -0.0000

Data Index: 1461993 (The Pile)

Max Activating Token Index: 346

Text #9

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2731. Min Act: -0.0000

Data Index: 343678 (The Pile)

Max Activating Token Index: 534

Text #10

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2780. Min Act: -0.0000

Data Index: 1931552 (The Pile)

Max Activating Token Index: 611

Text #11

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1822518 (The Pile)

Max Activating Token Index: 744

Text #12

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2643. Min Act: -0.0000

Data Index: 595096 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2657. Min Act: -0.0000

Data Index: 46805 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1167364 (The Pile)

Max Activating Token Index: 433

Text #15

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2587. Min Act: -0.0000

Data Index: 792003 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2598. Min Act: -0.0000

Data Index: 1535761 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1419512 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2570. Min Act: -0.0000

Data Index: 1532387 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 0.3727. Min Range: -0.3727

Max Act: 0.2388. Min Act: -0.0000

Data Index: 144507 (The Pile)

Max Activating Token Index: 814