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

Dataset: The Pile

Neuron 4706 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: 0.8790. Min Range: -0.8790

Max Act: 0.8650. Min Act: -0.0000

Data Index: 623724 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8650. Min Act: -0.0000

Data Index: 713870 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8790. Min Act: -0.0000

Data Index: 931766 (The Pile)

Max Activating Token Index: 202

Text #3

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8409. Min Act: -0.0000

Data Index: 359785 (The Pile)

Max Activating Token Index: 251

Text #4

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8131. Min Act: -0.0000

Data Index: 644413 (The Pile)

Max Activating Token Index: 127

Text #5

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7625. Min Act: -0.0000

Data Index: 455998 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8294. Min Act: -0.0000

Data Index: 19570 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8078. Min Act: -0.0000

Data Index: 602824 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1937797 (The Pile)

Max Activating Token Index: 232

Text #9

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7704. Min Act: -0.0000

Data Index: 234187 (The Pile)

Max Activating Token Index: 178

Text #10

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7758. Min Act: -0.0000

Data Index: 1247212 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1294282 (The Pile)

Max Activating Token Index: 442

Text #12

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7272. Min Act: -0.0000

Data Index: 275561 (The Pile)

Max Activating Token Index: 946

Text #13

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7971. Min Act: -0.0000

Data Index: 894334 (The Pile)

Max Activating Token Index: 186

Text #14

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7667. Min Act: -0.0000

Data Index: 778188 (The Pile)

Max Activating Token Index: 327

Text #15

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1420794 (The Pile)

Max Activating Token Index: 84

Text #16

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.8197. Min Act: -0.0000

Data Index: 40824 (The Pile)

Max Activating Token Index: 27

Text #17

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7341. Min Act: -0.0000

Data Index: 528181 (The Pile)

Max Activating Token Index: 372

Text #18

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7796. Min Act: -0.0000

Data Index: 879266 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.8790. Min Range: -0.8790

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1249362 (The Pile)

Max Activating Token Index: 133