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

Dataset: The Pile

Neuron 2741 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: 3.0125. Min Range: -3.0125

Max Act: 3.0125. Min Act: -0.0000

Data Index: 410733 (The Pile)

Max Activating Token Index: 54

Text #1

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.9853. Min Act: -0.0000

Data Index: 999791 (The Pile)

Max Activating Token Index: 517

Text #2

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.9655. Min Act: -0.0000

Data Index: 1292201 (The Pile)

Max Activating Token Index: 750

Text #3

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.8311. Min Act: -0.0000

Data Index: 1781951 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7607. Min Act: -0.0000

Data Index: 1310507 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.8587. Min Act: -0.0000

Data Index: 1205171 (The Pile)

Max Activating Token Index: 8

Text #6

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7613. Min Act: -0.0000

Data Index: 184371 (The Pile)

Max Activating Token Index: 3

Text #7

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7229. Min Act: -0.0000

Data Index: 613890 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7156. Min Act: -0.0000

Data Index: 1107491 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.5487. Min Act: -0.0000

Data Index: 1846909 (The Pile)

Max Activating Token Index: 117

Text #10

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.6317. Min Act: -0.0000

Data Index: 220469 (The Pile)

Max Activating Token Index: 926

Text #11

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1958965 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.7050. Min Act: -0.0000

Data Index: 775456 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.5413. Min Act: -0.0000

Data Index: 1007622 (The Pile)

Max Activating Token Index: 877

Text #14

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.6365. Min Act: -0.0000

Data Index: 506717 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.3586. Min Act: -0.0000

Data Index: 1567641 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.4638. Min Act: -0.0000

Data Index: 519326 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.5863. Min Act: -0.0000

Data Index: 863888 (The Pile)

Max Activating Token Index: 911

Text #18

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1723313 (The Pile)

Max Activating Token Index: 531

Text #19

Max Range: 3.0125. Min Range: -3.0125

Max Act: 2.2927. Min Act: -0.0000

Data Index: 1249699 (The Pile)

Max Activating Token Index: 850