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

Dataset: The Pile

Neuron 80 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3574. Min Act: -0.0000

Data Index: 934695 (The Pile)

Max Activating Token Index: 344

Text #1

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1096154 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3127. Min Act: -0.0000

Data Index: 1002721 (The Pile)

Max Activating Token Index: 22

Text #3

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2911. Min Act: -0.0000

Data Index: 1531779 (The Pile)

Max Activating Token Index: 109

Text #4

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2993. Min Act: -0.0000

Data Index: 661835 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.3078. Min Act: -0.0000

Data Index: 480401 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1580329 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2827. Min Act: -0.0000

Data Index: 897454 (The Pile)

Max Activating Token Index: 739

Text #8

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2976. Min Act: -0.0000

Data Index: 1960067 (The Pile)

Max Activating Token Index: 378

Text #9

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2835. Min Act: -0.0000

Data Index: 1557961 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2950. Min Act: -0.0000

Data Index: 551454 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2720. Min Act: -0.0000

Data Index: 1394865 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2560. Min Act: -0.0000

Data Index: 492999 (The Pile)

Max Activating Token Index: 929

Text #13

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1753991 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2710. Min Act: -0.0000

Data Index: 1126127 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2655. Min Act: -0.0000

Data Index: 96517 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2831. Min Act: -0.0000

Data Index: 833049 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1643618 (The Pile)

Max Activating Token Index: 118

Text #18

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2741. Min Act: -0.0000

Data Index: 979828 (The Pile)

Max Activating Token Index: 530

Text #19

Max Range: 0.3574. Min Range: -0.3574

Max Act: 0.2596. Min Act: -0.0000

Data Index: 1307146 (The Pile)

Max Activating Token Index: 299