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

Dataset: The Pile

Neuron 2867 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: 0.3121. Min Range: -0.3121

Max Act: 0.3079. Min Act: -0.0000

Data Index: 152992 (The Pile)

Max Activating Token Index: 242

Text #1

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3040. Min Act: -0.0000

Data Index: 202416 (The Pile)

Max Activating Token Index: 958

Text #2

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3121. Min Act: -0.0000

Data Index: 1002483 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3018. Min Act: -0.0000

Data Index: 1714774 (The Pile)

Max Activating Token Index: 904

Text #4

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1632918 (The Pile)

Max Activating Token Index: 908

Text #5

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1540711 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2914. Min Act: -0.0000

Data Index: 760234 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.3009. Min Act: -0.0000

Data Index: 1250442 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2844. Min Act: -0.0000

Data Index: 363581 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2940. Min Act: -0.0000

Data Index: 345058 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1322812 (The Pile)

Max Activating Token Index: 669

Text #11

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2776. Min Act: -0.0000

Data Index: 193369 (The Pile)

Max Activating Token Index: 994

Text #12

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1916755 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2818. Min Act: -0.0000

Data Index: 468938 (The Pile)

Max Activating Token Index: 250

Text #14

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2595. Min Act: -0.0000

Data Index: 311093 (The Pile)

Max Activating Token Index: 411

Text #15

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2688. Min Act: -0.0000

Data Index: 843332 (The Pile)

Max Activating Token Index: 443

Text #16

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2751. Min Act: -0.0000

Data Index: 1450243 (The Pile)

Max Activating Token Index: 177

Text #17

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2648. Min Act: -0.0000

Data Index: 903377 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2619. Min Act: -0.0000

Data Index: 224157 (The Pile)

Max Activating Token Index: 46

Text #19

Max Range: 0.3121. Min Range: -0.3121

Max Act: 0.2690. Min Act: -0.0000

Data Index: 263173 (The Pile)

Max Activating Token Index: 532