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

Dataset: The Pile

Neuron 1418 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1427680 (The Pile)

Max Activating Token Index: 881

Text #1

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.6220. Min Act: -0.0000

Data Index: 1639662 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1201697 (The Pile)

Max Activating Token Index: 784

Text #3

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.5264. Min Act: -0.0000

Data Index: 1955799 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.5015. Min Act: -0.0000

Data Index: 1839741 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4481. Min Act: -0.0000

Data Index: 571860 (The Pile)

Max Activating Token Index: 597

Text #6

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4582. Min Act: -0.0000

Data Index: 1291330 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4466. Min Act: -0.0000

Data Index: 507956 (The Pile)

Max Activating Token Index: 891

Text #8

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4556. Min Act: -0.0000

Data Index: 1206465 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4902. Min Act: -0.0000

Data Index: 250182 (The Pile)

Max Activating Token Index: 632

Text #10

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1523911 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4309. Min Act: -0.0000

Data Index: 559970 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3385. Min Act: -0.0000

Data Index: 830005 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3857. Min Act: -0.0000

Data Index: 1248785 (The Pile)

Max Activating Token Index: 351

Text #14

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.4007. Min Act: -0.0000

Data Index: 868248 (The Pile)

Max Activating Token Index: 556

Text #15

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3583. Min Act: -0.0000

Data Index: 1795712 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3489. Min Act: -0.0000

Data Index: 1574703 (The Pile)

Max Activating Token Index: 1007

Text #17

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3472. Min Act: -0.0000

Data Index: 1205384 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3075. Min Act: -0.0000

Data Index: 557485 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.6772. Min Range: -1.6772

Max Act: 1.3075. Min Act: -0.0000

Data Index: 277852 (The Pile)

Max Activating Token Index: 307