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

Dataset: The Pile

Neuron 351 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4897. Min Act: -0.0000

Data Index: 142046 (The Pile)

Max Activating Token Index: 913

Text #1

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.5120. Min Act: -0.0000

Data Index: 855100 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3932. Min Act: -0.0000

Data Index: 884860 (The Pile)

Max Activating Token Index: 356

Text #3

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4615. Min Act: -0.0000

Data Index: 834910 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3224. Min Act: -0.0000

Data Index: 1872699 (The Pile)

Max Activating Token Index: 710

Text #5

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3797. Min Act: -0.0000

Data Index: 1557930 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3765. Min Act: -0.0000

Data Index: 168057 (The Pile)

Max Activating Token Index: 519

Text #7

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3601. Min Act: -0.0000

Data Index: 623757 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4787. Min Act: -0.0000

Data Index: 1143869 (The Pile)

Max Activating Token Index: 574

Text #9

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.4617. Min Act: -0.0000

Data Index: 680351 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.2749. Min Act: -0.0000

Data Index: 1317776 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3094. Min Act: -0.0000

Data Index: 781616 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3343. Min Act: -0.0000

Data Index: 359585 (The Pile)

Max Activating Token Index: 453

Text #13

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.1619. Min Act: -0.0000

Data Index: 1493483 (The Pile)

Max Activating Token Index: 760

Text #14

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.1582. Min Act: -0.0000

Data Index: 813924 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3055. Min Act: -0.0000

Data Index: 1721687 (The Pile)

Max Activating Token Index: 159

Text #16

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3029. Min Act: -0.0000

Data Index: 1713976 (The Pile)

Max Activating Token Index: 430

Text #17

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.3148. Min Act: -0.0000

Data Index: 668670 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.2316. Min Act: -0.0000

Data Index: 815907 (The Pile)

Max Activating Token Index: 849

Text #19

Max Range: 1.5120. Min Range: -1.5120

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1846700 (The Pile)

Max Activating Token Index: 710