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

Dataset: The Pile

Neuron 1443 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1904864 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.9380. Min Act: -0.0000

Data Index: 1143219 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8609. Min Act: -0.0000

Data Index: 667329 (The Pile)

Max Activating Token Index: 902

Text #3

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8425. Min Act: -0.0000

Data Index: 918999 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8453. Min Act: -0.0000

Data Index: 269610 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1742594 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1297165 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1688339 (The Pile)

Max Activating Token Index: 142

Text #8

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7939. Min Act: -0.0000

Data Index: 706823 (The Pile)

Max Activating Token Index: 340

Text #9

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7880. Min Act: -0.0000

Data Index: 897533 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8762. Min Act: -0.0000

Data Index: 241287 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.8609. Min Act: -0.0000

Data Index: 80640 (The Pile)

Max Activating Token Index: 85

Text #12

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7988. Min Act: -0.0000

Data Index: 410634 (The Pile)

Max Activating Token Index: 350

Text #13

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7832. Min Act: -0.0000

Data Index: 555007 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7584. Min Act: -0.0000

Data Index: 1840922 (The Pile)

Max Activating Token Index: 122

Text #15

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.6856. Min Act: -0.0000

Data Index: 1979982 (The Pile)

Max Activating Token Index: 1006

Text #16

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7881. Min Act: -0.0000

Data Index: 1792286 (The Pile)

Max Activating Token Index: 966

Text #17

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7874. Min Act: -0.0000

Data Index: 118364 (The Pile)

Max Activating Token Index: 32

Text #18

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7665. Min Act: -0.0000

Data Index: 630380 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.9705. Min Range: -0.9705

Max Act: 0.7432. Min Act: -0.0000

Data Index: 772036 (The Pile)

Max Activating Token Index: 634