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

Dataset: The Pile

Neuron 1892 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: 0.3018. Min Range: -0.3018

Max Act: 0.3018. Min Act: -0.0000

Data Index: 90622 (The Pile)

Max Activating Token Index: 364

Text #1

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1237050 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2926. Min Act: -0.0000

Data Index: 449445 (The Pile)

Max Activating Token Index: 945

Text #3

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2680. Min Act: -0.0000

Data Index: 544339 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2848. Min Act: -0.0000

Data Index: 1416114 (The Pile)

Max Activating Token Index: 375

Text #5

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1363971 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2791. Min Act: -0.0000

Data Index: 1284523 (The Pile)

Max Activating Token Index: 91

Text #7

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2866. Min Act: -0.0000

Data Index: 847693 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2841. Min Act: -0.0000

Data Index: 1051298 (The Pile)

Max Activating Token Index: 824

Text #9

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2531. Min Act: -0.0000

Data Index: 703078 (The Pile)

Max Activating Token Index: 928

Text #10

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2710. Min Act: -0.0000

Data Index: 46244 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1041191 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2721. Min Act: -0.0000

Data Index: 215374 (The Pile)

Max Activating Token Index: 893

Text #13

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1503446 (The Pile)

Max Activating Token Index: 804

Text #14

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2678. Min Act: -0.0000

Data Index: 684132 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1763207 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2738. Min Act: -0.0000

Data Index: 832723 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1867253 (The Pile)

Max Activating Token Index: 315

Text #18

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2525. Min Act: -0.0000

Data Index: 1691592 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 0.3018. Min Range: -0.3018

Max Act: 0.2572. Min Act: -0.0000

Data Index: 677791 (The Pile)

Max Activating Token Index: 550