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

Dataset: The Pile

Neuron 2133 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: 1.0055. Min Range: -1.0055

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1533135 (The Pile)

Max Activating Token Index: 601

Text #1

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9692. Min Act: -0.0000

Data Index: 273633 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1619431 (The Pile)

Max Activating Token Index: 756

Text #3

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9467. Min Act: -0.0000

Data Index: 877091 (The Pile)

Max Activating Token Index: 905

Text #4

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9389. Min Act: -0.0000

Data Index: 940755 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8487. Min Act: -0.0000

Data Index: 589282 (The Pile)

Max Activating Token Index: 698

Text #6

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1194897 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9217. Min Act: -0.0000

Data Index: 971971 (The Pile)

Max Activating Token Index: 146

Text #8

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8404. Min Act: -0.0000

Data Index: 382106 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8256. Min Act: -0.0000

Data Index: 124506 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1800134 (The Pile)

Max Activating Token Index: 912

Text #11

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8956. Min Act: -0.0000

Data Index: 800585 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1802272 (The Pile)

Max Activating Token Index: 853

Text #13

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1600132 (The Pile)

Max Activating Token Index: 833

Text #14

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7862. Min Act: -0.0000

Data Index: 1093640 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7872. Min Act: -0.0000

Data Index: 563751 (The Pile)

Max Activating Token Index: 537

Text #16

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1241617 (The Pile)

Max Activating Token Index: 637

Text #17

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1480169 (The Pile)

Max Activating Token Index: 883

Text #18

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1692202 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 1.0055. Min Range: -1.0055

Max Act: 0.8073. Min Act: -0.0000

Data Index: 1754253 (The Pile)

Max Activating Token Index: 360