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

Dataset: The Pile

Neuron 1488 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: 0.7942. Min Range: -0.7942

Max Act: 0.7942. Min Act: -0.0000

Data Index: 522283 (The Pile)

Max Activating Token Index: 851

Text #1

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6846. Min Act: -0.0000

Data Index: 1353954 (The Pile)

Max Activating Token Index: 563

Text #2

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1200597 (The Pile)

Max Activating Token Index: 963

Text #3

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1257671 (The Pile)

Max Activating Token Index: 798

Text #4

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6787. Min Act: -0.0000

Data Index: 33490 (The Pile)

Max Activating Token Index: 910

Text #5

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1062483 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6527. Min Act: -0.0000

Data Index: 568076 (The Pile)

Max Activating Token Index: 487

Text #7

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6254. Min Act: -0.0000

Data Index: 466400 (The Pile)

Max Activating Token Index: 512

Text #8

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6688. Min Act: -0.0000

Data Index: 58430 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6258. Min Act: -0.0000

Data Index: 445620 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6218. Min Act: -0.0000

Data Index: 1701876 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.7027. Min Act: -0.0000

Data Index: 470153 (The Pile)

Max Activating Token Index: 529

Text #12

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1597260 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1094834 (The Pile)

Max Activating Token Index: 88

Text #14

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6034. Min Act: -0.0000

Data Index: 181079 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6081. Min Act: -0.0000

Data Index: 900616 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6498. Min Act: -0.0000

Data Index: 1777940 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.5749. Min Act: -0.0000

Data Index: 685042 (The Pile)

Max Activating Token Index: 856

Text #18

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6707. Min Act: -0.0000

Data Index: 869518 (The Pile)

Max Activating Token Index: 705

Text #19

Max Range: 0.7942. Min Range: -0.7942

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1703686 (The Pile)

Max Activating Token Index: 963