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

Dataset: The Pile

Neuron 924 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: 8.1756. Min Range: -8.1756

Max Act: 8.1756. Min Act: -0.0000

Data Index: 1116406 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.9566. Min Act: -0.0000

Data Index: 788753 (The Pile)

Max Activating Token Index: 883

Text #2

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.5824. Min Act: -0.0000

Data Index: 213095 (The Pile)

Max Activating Token Index: 434

Text #3

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.5980. Min Act: -0.0000

Data Index: 1725836 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.7631. Min Act: -0.0000

Data Index: 803797 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.8148. Min Act: -0.0000

Data Index: 1092448 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 8.1756. Min Range: -8.1756

Max Act: 5.8557. Min Act: -0.0000

Data Index: 1257594 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.0374. Min Act: -0.0000

Data Index: 1706332 (The Pile)

Max Activating Token Index: 972

Text #8

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.2471. Min Act: -0.0000

Data Index: 123852 (The Pile)

Max Activating Token Index: 1008

Text #9

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.7951. Min Act: -0.0000

Data Index: 1292318 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.6083. Min Act: -0.0000

Data Index: 290988 (The Pile)

Max Activating Token Index: 57

Text #11

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.7639. Min Act: -0.0000

Data Index: 1977654 (The Pile)

Max Activating Token Index: 682

Text #12

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.4789. Min Act: -0.0000

Data Index: 935117 (The Pile)

Max Activating Token Index: 849

Text #13

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.9157. Min Act: -0.0000

Data Index: 1371261 (The Pile)

Max Activating Token Index: 587

Text #14

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.9352. Min Act: -0.0000

Data Index: 1105056 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.9523. Min Act: -0.0000

Data Index: 1177186 (The Pile)

Max Activating Token Index: 715

Text #16

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.7146. Min Act: -0.0000

Data Index: 852531 (The Pile)

Max Activating Token Index: 678

Text #17

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.2505. Min Act: -0.0000

Data Index: 1703474 (The Pile)

Max Activating Token Index: 984

Text #18

Max Range: 8.1756. Min Range: -8.1756

Max Act: 7.0163. Min Act: -0.0000

Data Index: 45707 (The Pile)

Max Activating Token Index: 633

Text #19

Max Range: 8.1756. Min Range: -8.1756

Max Act: 6.5217. Min Act: -0.0000

Data Index: 582475 (The Pile)

Max Activating Token Index: 765