Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 593 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1015. Min Act: -0.0004

Data Index: 527552 (The Pile)

Max Activating Token Index: 619

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1011. Min Act: -0.0004

Data Index: 1926863 (The Pile)

Max Activating Token Index: 596

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0964. Min Act: -0.0004

Data Index: 1311308 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: -0.0004

Data Index: 881870 (The Pile)

Max Activating Token Index: 263

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0983. Min Act: -0.0004

Data Index: 962356 (The Pile)

Max Activating Token Index: 456

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1005. Min Act: -0.0004

Data Index: 1942547 (The Pile)

Max Activating Token Index: 359

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0984. Min Act: -0.0004

Data Index: 1914283 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0976. Min Act: -0.0004

Data Index: 789061 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0947. Min Act: -0.0004

Data Index: 754206 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0962. Min Act: -0.0004

Data Index: 1103856 (The Pile)

Max Activating Token Index: 824

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0934. Min Act: -0.0004

Data Index: 1553850 (The Pile)

Max Activating Token Index: 711

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0967. Min Act: -0.0004

Data Index: 353389 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0947. Min Act: -0.0004

Data Index: 823947 (The Pile)

Max Activating Token Index: 998

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0947. Min Act: -0.0004

Data Index: 915156 (The Pile)

Max Activating Token Index: 215

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0978. Min Act: -0.0004

Data Index: 1843724 (The Pile)

Max Activating Token Index: 507

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0913. Min Act: -0.0004

Data Index: 1479898 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0924. Min Act: -0.0004

Data Index: 1554259 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0903. Min Act: -0.0004

Data Index: 1730663 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0904. Min Act: -0.0004

Data Index: 1057565 (The Pile)

Max Activating Token Index: 360

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0960. Min Act: -0.0004

Data Index: 1631078 (The Pile)

Max Activating Token Index: 932