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

Dataset: The Pile

Neuron 772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2514. Min Range: -7.2514

Max Act: 7.2514. Min Act: -0.0000

Data Index: 514967 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 7.2514. Min Range: -7.2514

Max Act: 7.0348. Min Act: -0.0000

Data Index: 786805 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 7.2514. Min Range: -7.2514

Max Act: 6.6786. Min Act: -0.0000

Data Index: 385966 (The Pile)

Max Activating Token Index: 531

Text #3

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.9997. Min Act: -0.0000

Data Index: 1370200 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.9703. Min Act: -0.0000

Data Index: 832488 (The Pile)

Max Activating Token Index: 848

Text #5

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.7876. Min Act: -0.0000

Data Index: 1970542 (The Pile)

Max Activating Token Index: 268

Text #6

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.9893. Min Act: -0.0000

Data Index: 1015654 (The Pile)

Max Activating Token Index: 794

Text #7

Max Range: 7.2514. Min Range: -7.2514

Max Act: 5.2596. Min Act: -0.0000

Data Index: 1493109 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 7.2514. Min Range: -7.2514

Max Act: 5.6351. Min Act: -0.0000

Data Index: 512737 (The Pile)

Max Activating Token Index: 916

Text #9

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.4230. Min Act: 0.0000

Data Index: 1023782 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.4192. Min Act: -0.0000

Data Index: 1971439 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.4586. Min Act: -0.0000

Data Index: 1043955 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.3976. Min Act: -0.0000

Data Index: 619199 (The Pile)

Max Activating Token Index: 250

Text #13

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.1240. Min Act: -0.0000

Data Index: 1962993 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.6594. Min Act: -0.0000

Data Index: 1592286 (The Pile)

Max Activating Token Index: 484

Text #15

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.1089. Min Act: -0.0000

Data Index: 1706142 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 7.2514. Min Range: -7.2514

Max Act: 3.8143. Min Act: -0.0000

Data Index: 1528430 (The Pile)

Max Activating Token Index: 938

Text #17

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.1924. Min Act: -0.0000

Data Index: 1934107 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.2764. Min Act: -0.0000

Data Index: 1137631 (The Pile)

Max Activating Token Index: 447

Text #19

Max Range: 7.2514. Min Range: -7.2514

Max Act: 4.0878. Min Act: -0.0000

Data Index: 1909152 (The Pile)

Max Activating Token Index: 376