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

Dataset: The Pile

Neuron 2381 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.1296. Min Act: -0.0000

Data Index: 1153389 (The Pile)

Max Activating Token Index: 626

Text #1

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.0894. Min Act: -0.0000

Data Index: 100288 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.0780. Min Act: -0.0000

Data Index: 1149737 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 1.1296. Min Range: -1.1296

Max Act: 1.0004. Min Act: -0.0000

Data Index: 155819 (The Pile)

Max Activating Token Index: 136

Text #4

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9574. Min Act: -0.0000

Data Index: 810689 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8937. Min Act: -0.0000

Data Index: 662087 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9546. Min Act: -0.0000

Data Index: 257761 (The Pile)

Max Activating Token Index: 859

Text #7

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1175969 (The Pile)

Max Activating Token Index: 598

Text #8

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9334. Min Act: -0.0000

Data Index: 923674 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1505446 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8684. Min Act: -0.0000

Data Index: 532543 (The Pile)

Max Activating Token Index: 599

Text #11

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8995. Min Act: -0.0000

Data Index: 326937 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8250. Min Act: -0.0000

Data Index: 1186449 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1363306 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8448. Min Act: -0.0000

Data Index: 717175 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8117. Min Act: -0.0000

Data Index: 762525 (The Pile)

Max Activating Token Index: 698

Text #16

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.8784. Min Act: -0.0000

Data Index: 1771769 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7983. Min Act: -0.0000

Data Index: 780798 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7980. Min Act: -0.0000

Data Index: 786041 (The Pile)

Max Activating Token Index: 997

Text #19

Max Range: 1.1296. Min Range: -1.1296

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1336431 (The Pile)

Max Activating Token Index: 713