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

Dataset: The Pile

Neuron 4086 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: 0.3405. Min Range: -0.3405

Max Act: 0.3347. Min Act: -0.0000

Data Index: 534512 (The Pile)

Max Activating Token Index: 537

Text #1

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1893425 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1107899 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3405. Min Act: -0.0000

Data Index: 716566 (The Pile)

Max Activating Token Index: 542

Text #4

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1022742 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3060. Min Act: -0.0000

Data Index: 706013 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2960. Min Act: -0.0000

Data Index: 1100980 (The Pile)

Max Activating Token Index: 880

Text #7

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2823. Min Act: -0.0000

Data Index: 488160 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2864. Min Act: -0.0000

Data Index: 520886 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2762. Min Act: -0.0000

Data Index: 571896 (The Pile)

Max Activating Token Index: 96

Text #10

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1951510 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1679888 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2893. Min Act: -0.0000

Data Index: 1195736 (The Pile)

Max Activating Token Index: 918

Text #13

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2569. Min Act: -0.0000

Data Index: 229971 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2904. Min Act: -0.0000

Data Index: 1791383 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3104. Min Act: -0.0000

Data Index: 823315 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2875. Min Act: -0.0000

Data Index: 323214 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1880390 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3171. Min Act: -0.0000

Data Index: 603310 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2781. Min Act: -0.0000

Data Index: 1795663 (The Pile)

Max Activating Token Index: 953