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

Dataset: The Pile

Neuron 4251 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.3815. Min Act: -0.0000

Data Index: 1725428 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2855. Min Act: -0.0000

Data Index: 1425169 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.2742. Min Act: -0.0000

Data Index: 897556 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.3961. Min Act: -0.0000

Data Index: 1887955 (The Pile)

Max Activating Token Index: 296

Text #4

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.0531. Min Act: -0.0000

Data Index: 1803261 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.0328. Min Act: -0.0000

Data Index: 425759 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1331. Min Act: -0.0000

Data Index: 1513995 (The Pile)

Max Activating Token Index: 424

Text #7

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.7976. Min Act: -0.0000

Data Index: 62184 (The Pile)

Max Activating Token Index: 21

Text #8

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.7877. Min Act: -0.0000

Data Index: 1058863 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.0722. Min Act: -0.0000

Data Index: 1467043 (The Pile)

Max Activating Token Index: 607

Text #10

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.0863. Min Act: -0.0000

Data Index: 40113 (The Pile)

Max Activating Token Index: 866

Text #11

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.7728. Min Act: -0.0000

Data Index: 332849 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.9190. Min Act: -0.0000

Data Index: 666037 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.0721. Min Act: -0.0000

Data Index: 1764477 (The Pile)

Max Activating Token Index: 192

Text #14

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.9091. Min Act: -0.0000

Data Index: 1373463 (The Pile)

Max Activating Token Index: 472

Text #15

Max Range: 3.3961. Min Range: -3.3961

Max Act: 3.1813. Min Act: -0.0000

Data Index: 1346840 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.8697. Min Act: -0.0000

Data Index: 1200383 (The Pile)

Max Activating Token Index: 192

Text #17

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.8496. Min Act: -0.0000

Data Index: 576009 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.8458. Min Act: -0.0000

Data Index: 170675 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 3.3961. Min Range: -3.3961

Max Act: 2.6718. Min Act: -0.0000

Data Index: 1067375 (The Pile)

Max Activating Token Index: 322