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

Dataset: The Pile

Neuron 67 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: 0.2965. Min Range: -0.2965

Max Act: 0.2965. Min Act: -0.0000

Data Index: 28421 (The Pile)

Max Activating Token Index: 215

Text #1

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2686. Min Act: -0.0000

Data Index: 1034837 (The Pile)

Max Activating Token Index: 461

Text #2

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1316445 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2710. Min Act: -0.0000

Data Index: 974171 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2467. Min Act: -0.0000

Data Index: 1729551 (The Pile)

Max Activating Token Index: 455

Text #5

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2501. Min Act: -0.0000

Data Index: 1989413 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1045640 (The Pile)

Max Activating Token Index: 42

Text #7

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2546. Min Act: -0.0000

Data Index: 752425 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1366109 (The Pile)

Max Activating Token Index: 984

Text #9

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1712509 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2299. Min Act: -0.0000

Data Index: 320315 (The Pile)

Max Activating Token Index: 443

Text #11

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2291. Min Act: -0.0000

Data Index: 1459200 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2425. Min Act: -0.0000

Data Index: 241944 (The Pile)

Max Activating Token Index: 832

Text #13

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1948678 (The Pile)

Max Activating Token Index: 552

Text #14

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1233473 (The Pile)

Max Activating Token Index: 976

Text #15

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2224. Min Act: -0.0000

Data Index: 1392770 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2352. Min Act: -0.0000

Data Index: 651531 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2179. Min Act: -0.0000

Data Index: 394836 (The Pile)

Max Activating Token Index: 38

Text #18

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2036. Min Act: -0.0000

Data Index: 904250 (The Pile)

Max Activating Token Index: 585

Text #19

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.1959. Min Act: -0.0000

Data Index: 826517 (The Pile)

Max Activating Token Index: 906