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

Dataset: The Pile

Neuron 2763 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: 11.2633. Min Range: -11.2633

Max Act: 10.8179. Min Act: -0.0000

Data Index: 184333 (The Pile)

Max Activating Token Index: 494

Text #1

Max Range: 11.2633. Min Range: -11.2633

Max Act: 11.2633. Min Act: -0.0000

Data Index: 139742 (The Pile)

Max Activating Token Index: 573

Text #2

Max Range: 11.2633. Min Range: -11.2633

Max Act: 11.0694. Min Act: -0.0000

Data Index: 1648108 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 11.2633. Min Range: -11.2633

Max Act: 10.8451. Min Act: -0.0000

Data Index: 1878449 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 11.2633. Min Range: -11.2633

Max Act: 10.5593. Min Act: -0.0000

Data Index: 477930 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 11.2633. Min Range: -11.2633

Max Act: 10.5917. Min Act: -0.0000

Data Index: 985062 (The Pile)

Max Activating Token Index: 835

Text #6

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.8308. Min Act: -0.0000

Data Index: 841783 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 11.2633. Min Range: -11.2633

Max Act: 10.1448. Min Act: -0.0000

Data Index: 1646127 (The Pile)

Max Activating Token Index: 773

Text #8

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.6557. Min Act: -0.0000

Data Index: 1679248 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.2013. Min Act: -0.0000

Data Index: 341825 (The Pile)

Max Activating Token Index: 561

Text #10

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.8164. Min Act: -0.0000

Data Index: 532858 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.8081. Min Act: -0.0000

Data Index: 1350091 (The Pile)

Max Activating Token Index: 661

Text #12

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.4243. Min Act: -0.0000

Data Index: 807362 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.2578. Min Act: -0.0000

Data Index: 1981005 (The Pile)

Max Activating Token Index: 756

Text #14

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.2711. Min Act: -0.0000

Data Index: 1340381 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.2025. Min Act: -0.0000

Data Index: 1942089 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 11.2633. Min Range: -11.2633

Max Act: 8.8766. Min Act: -0.0000

Data Index: 876565 (The Pile)

Max Activating Token Index: 596

Text #17

Max Range: 11.2633. Min Range: -11.2633

Max Act: 9.2044. Min Act: -0.0000

Data Index: 765818 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 11.2633. Min Range: -11.2633

Max Act: 8.6219. Min Act: -0.0000

Data Index: 1818896 (The Pile)

Max Activating Token Index: 501

Text #19

Max Range: 11.2633. Min Range: -11.2633

Max Act: 8.6987. Min Act: -0.0000

Data Index: 50909 (The Pile)

Max Activating Token Index: 737