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

Dataset: The Pile

Neuron 1211 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: 0.9135. Min Range: -0.9135

Max Act: 0.8930. Min Act: -0.0000

Data Index: 1827152 (The Pile)

Max Activating Token Index: 62

Text #1

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.9135. Min Act: -0.0000

Data Index: 1483646 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.8734. Min Act: -0.0000

Data Index: 1964771 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.8207. Min Act: -0.0000

Data Index: 138900 (The Pile)

Max Activating Token Index: 547

Text #4

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.8738. Min Act: -0.0000

Data Index: 1830869 (The Pile)

Max Activating Token Index: 226

Text #5

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1957826 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7563. Min Act: -0.0000

Data Index: 208149 (The Pile)

Max Activating Token Index: 551

Text #7

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1186940 (The Pile)

Max Activating Token Index: 831

Text #8

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1997181 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7805. Min Act: -0.0000

Data Index: 575857 (The Pile)

Max Activating Token Index: 316

Text #10

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7537. Min Act: -0.0000

Data Index: 757209 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7338. Min Act: -0.0000

Data Index: 89977 (The Pile)

Max Activating Token Index: 1022

Text #12

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7653. Min Act: -0.0000

Data Index: 657927 (The Pile)

Max Activating Token Index: 877

Text #13

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1424851 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1688517 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7634. Min Act: -0.0000

Data Index: 1118600 (The Pile)

Max Activating Token Index: 737

Text #16

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7334. Min Act: -0.0000

Data Index: 154484 (The Pile)

Max Activating Token Index: 499

Text #17

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7268. Min Act: -0.0000

Data Index: 1579933 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7508. Min Act: -0.0000

Data Index: 397605 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 0.9135. Min Range: -0.9135

Max Act: 0.7030. Min Act: -0.0000

Data Index: 90282 (The Pile)

Max Activating Token Index: 313