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

Dataset: The Pile

Neuron 3280 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: 0.3020. Min Range: -0.3020

Max Act: 0.2786. Min Act: -0.0000

Data Index: 1829309 (The Pile)

Max Activating Token Index: 658

Text #1

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2887. Min Act: -0.0000

Data Index: 1585843 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2861. Min Act: -0.0000

Data Index: 35630 (The Pile)

Max Activating Token Index: 451

Text #3

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.3020. Min Act: -0.0000

Data Index: 1023118 (The Pile)

Max Activating Token Index: 244

Text #4

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2894. Min Act: -0.0000

Data Index: 740615 (The Pile)

Max Activating Token Index: 841

Text #5

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2799. Min Act: -0.0000

Data Index: 503218 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2769. Min Act: -0.0000

Data Index: 49473 (The Pile)

Max Activating Token Index: 645

Text #7

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1427258 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1863185 (The Pile)

Max Activating Token Index: 827

Text #9

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2627. Min Act: -0.0000

Data Index: 149888 (The Pile)

Max Activating Token Index: 446

Text #10

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2657. Min Act: -0.0000

Data Index: 10832 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1624260 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2942. Min Act: -0.0000

Data Index: 499588 (The Pile)

Max Activating Token Index: 963

Text #13

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2486. Min Act: -0.0000

Data Index: 467304 (The Pile)

Max Activating Token Index: 808

Text #14

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2524. Min Act: -0.0000

Data Index: 341302 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2674. Min Act: -0.0000

Data Index: 592324 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2546. Min Act: -0.0000

Data Index: 674508 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1571890 (The Pile)

Max Activating Token Index: 789

Text #18

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1195844 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 0.3020. Min Range: -0.3020

Max Act: 0.2836. Min Act: -0.0000

Data Index: 75936 (The Pile)

Max Activating Token Index: 760