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

Dataset: The Pile

Neuron 3591 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: 0.3597. Min Range: -0.3597

Max Act: 0.3522. Min Act: -0.0000

Data Index: 174118 (The Pile)

Max Activating Token Index: 6

Text #1

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1622446 (The Pile)

Max Activating Token Index: 579

Text #2

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3597. Min Act: -0.0000

Data Index: 1215600 (The Pile)

Max Activating Token Index: 231

Text #3

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3420. Min Act: -0.0000

Data Index: 1240999 (The Pile)

Max Activating Token Index: 226

Text #4

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3499. Min Act: -0.0000

Data Index: 1742955 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1835847 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1325433 (The Pile)

Max Activating Token Index: 17

Text #7

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1505520 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3228. Min Act: -0.0000

Data Index: 1191954 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3241. Min Act: -0.0000

Data Index: 1570344 (The Pile)

Max Activating Token Index: 290

Text #10

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3253. Min Act: -0.0000

Data Index: 531008 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1680888 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3113. Min Act: -0.0000

Data Index: 8612 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3167. Min Act: -0.0000

Data Index: 653884 (The Pile)

Max Activating Token Index: 187

Text #14

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1643563 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3101. Min Act: -0.0000

Data Index: 712083 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3270. Min Act: -0.0000

Data Index: 478339 (The Pile)

Max Activating Token Index: 961

Text #17

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3047. Min Act: -0.0000

Data Index: 1257731 (The Pile)

Max Activating Token Index: 349

Text #18

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.2914. Min Act: -0.0000

Data Index: 500330 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.3597. Min Range: -0.3597

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1012976 (The Pile)

Max Activating Token Index: 38