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

Dataset: The Pile

Neuron 2610 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.3371. Min Act: -0.0000

Data Index: 923938 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.2058. Min Act: -0.0000

Data Index: 106923 (The Pile)

Max Activating Token Index: 434

Text #2

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.2039. Min Act: -0.0000

Data Index: 1175256 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.3371. Min Range: -1.3371

Max Act: 1.1347. Min Act: -0.0000

Data Index: 1272735 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.9495. Min Act: -0.0000

Data Index: 1187684 (The Pile)

Max Activating Token Index: 476

Text #5

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1933833 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.9291. Min Act: -0.0000

Data Index: 1890186 (The Pile)

Max Activating Token Index: 624

Text #7

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.9352. Min Act: -0.0000

Data Index: 452925 (The Pile)

Max Activating Token Index: 330

Text #8

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1634207 (The Pile)

Max Activating Token Index: 509

Text #9

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.9349. Min Act: -0.0000

Data Index: 1254110 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.8794. Min Act: -0.0000

Data Index: 976169 (The Pile)

Max Activating Token Index: 666

Text #11

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1505615 (The Pile)

Max Activating Token Index: 391

Text #12

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1014094 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.8401. Min Act: -0.0000

Data Index: 886085 (The Pile)

Max Activating Token Index: 402

Text #14

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1203042 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.7905. Min Act: -0.0000

Data Index: 879393 (The Pile)

Max Activating Token Index: 247

Text #16

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.8115. Min Act: -0.0000

Data Index: 634029 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1350226 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1426043 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.3371. Min Range: -1.3371

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1977013 (The Pile)

Max Activating Token Index: 417