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

Dataset: The Pile

Neuron 1179 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2552. Min Act: -0.0000

Data Index: 313786 (The Pile)

Max Activating Token Index: 814

Text #1

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1925303 (The Pile)

Max Activating Token Index: 625

Text #2

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.2484. Min Act: -0.0000

Data Index: 1659561 (The Pile)

Max Activating Token Index: 898

Text #3

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1573. Min Act: -0.0000

Data Index: 1793842 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.1956. Min Act: -0.0000

Data Index: 243965 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0583. Min Act: -0.0000

Data Index: 318177 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0334. Min Act: -0.0000

Data Index: 107711 (The Pile)

Max Activating Token Index: 822

Text #7

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0295. Min Act: -0.0000

Data Index: 1077282 (The Pile)

Max Activating Token Index: 521

Text #8

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0307. Min Act: -0.0000

Data Index: 343133 (The Pile)

Max Activating Token Index: 890

Text #9

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0059. Min Act: -0.0000

Data Index: 927914 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.2671. Min Range: -1.2671

Max Act: 1.0072. Min Act: -0.0000

Data Index: 728234 (The Pile)

Max Activating Token Index: 277

Text #11

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9688. Min Act: -0.0000

Data Index: 1879394 (The Pile)

Max Activating Token Index: 900

Text #12

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9385. Min Act: -0.0000

Data Index: 384820 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9977. Min Act: -0.0000

Data Index: 1618949 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9702. Min Act: -0.0000

Data Index: 175173 (The Pile)

Max Activating Token Index: 683

Text #15

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9032. Min Act: -0.0000

Data Index: 1323159 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9562. Min Act: -0.0000

Data Index: 945792 (The Pile)

Max Activating Token Index: 52

Text #17

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9997. Min Act: -0.0000

Data Index: 169281 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1547495 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 1.2671. Min Range: -1.2671

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1746756 (The Pile)

Max Activating Token Index: 955