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

Dataset: The Pile

Neuron 2931 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0055. Min Act: -0.0000

Data Index: 1560536 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0055. Min Act: -0.0000

Data Index: 749720 (The Pile)

Max Activating Token Index: 450

Text #2

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0052. Min Act: -0.0000

Data Index: 211546 (The Pile)

Max Activating Token Index: 443

Text #3

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0053. Min Act: -0.0000

Data Index: 1576366 (The Pile)

Max Activating Token Index: 552

Text #4

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0051. Min Act: -0.0000

Data Index: 1162675 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0051. Min Act: -0.0000

Data Index: 1225107 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0050. Min Act: -0.0000

Data Index: 221882 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0000

Data Index: 928350 (The Pile)

Max Activating Token Index: 567

Text #8

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0000

Data Index: 1219729 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0001

Data Index: 1053875 (The Pile)

Max Activating Token Index: 448

Text #10

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0000

Data Index: 347454 (The Pile)

Max Activating Token Index: 604

Text #11

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 1314950 (The Pile)

Max Activating Token Index: 377

Text #12

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 193638 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0001

Data Index: 1991122 (The Pile)

Max Activating Token Index: 523

Text #14

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 1299131 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 224921 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 1796331 (The Pile)

Max Activating Token Index: 597

Text #17

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 1873779 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0048. Min Act: -0.0000

Data Index: 32535 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 0.0055. Min Range: -0.0055

Max Act: 0.0049. Min Act: -0.0000

Data Index: 451248 (The Pile)

Max Activating Token Index: 385