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

Dataset: The Pile

Neuron 3947 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: 1.0007. Min Range: -1.0007

Max Act: 1.0007. Min Act: -0.0000

Data Index: 172317 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8421. Min Act: -0.0000

Data Index: 1429235 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1158869 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7635. Min Act: -0.0000

Data Index: 641758 (The Pile)

Max Activating Token Index: 941

Text #4

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7399. Min Act: 0.0000

Data Index: 558754 (The Pile)

Max Activating Token Index: 319

Text #5

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1473770 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7732. Min Act: 0.0000

Data Index: 718782 (The Pile)

Max Activating Token Index: 678

Text #7

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7546. Min Act: 0.0001

Data Index: 1970030 (The Pile)

Max Activating Token Index: 953

Text #8

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7661. Min Act: 0.0000

Data Index: 163945 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7582. Min Act: -0.0000

Data Index: 762766 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7979. Min Act: 0.0000

Data Index: 90554 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7071. Min Act: 0.0000

Data Index: 681624 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7485. Min Act: 0.0000

Data Index: 347148 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7338. Min Act: 0.0000

Data Index: 1848931 (The Pile)

Max Activating Token Index: 692

Text #14

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1757717 (The Pile)

Max Activating Token Index: 709

Text #15

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.6850. Min Act: -0.0000

Data Index: 385875 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1274530 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.6716. Min Act: 0.0000

Data Index: 305427 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1517422 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 1.0007. Min Range: -1.0007

Max Act: 0.7474. Min Act: -0.0000

Data Index: 1062127 (The Pile)

Max Activating Token Index: 134