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

Dataset: The Pile

Neuron 3390 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1160. Min Range: -3.1160

Max Act: 3.0652. Min Act: -0.0000

Data Index: 1902675 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 3.1160. Min Range: -3.1160

Max Act: 3.1160. Min Act: -0.0000

Data Index: 11013 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 3.1160. Min Range: -3.1160

Max Act: 3.0476. Min Act: -0.0000

Data Index: 1031709 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 3.1160. Min Range: -3.1160

Max Act: 3.0137. Min Act: -0.0000

Data Index: 1649338 (The Pile)

Max Activating Token Index: 336

Text #4

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.9729. Min Act: -0.0000

Data Index: 1407962 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.9738. Min Act: -0.0000

Data Index: 71747 (The Pile)

Max Activating Token Index: 754

Text #6

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.9666. Min Act: -0.0000

Data Index: 147208 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.9189. Min Act: -0.0000

Data Index: 382532 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.8657. Min Act: -0.0000

Data Index: 558091 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.7333. Min Act: -0.0000

Data Index: 424955 (The Pile)

Max Activating Token Index: 813

Text #10

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.7278. Min Act: -0.0000

Data Index: 1965256 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.7524. Min Act: -0.0000

Data Index: 330300 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.9485. Min Act: -0.0000

Data Index: 712105 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.6370. Min Act: -0.0000

Data Index: 1805568 (The Pile)

Max Activating Token Index: 498

Text #14

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.7905. Min Act: -0.0000

Data Index: 543617 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.8362. Min Act: -0.0000

Data Index: 1823055 (The Pile)

Max Activating Token Index: 983

Text #16

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.7633. Min Act: -0.0000

Data Index: 81500 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1020856 (The Pile)

Max Activating Token Index: 615

Text #18

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.8472. Min Act: -0.0000

Data Index: 1569892 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 3.1160. Min Range: -3.1160

Max Act: 2.8405. Min Act: -0.0000

Data Index: 1161608 (The Pile)

Max Activating Token Index: 211