Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2899 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0000

Data Index: 866731 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6610. Min Act: -0.0000

Data Index: 1563992 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6579. Min Act: -0.0000

Data Index: 790566 (The Pile)

Max Activating Token Index: 525

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5779. Min Act: -0.0000

Data Index: 1372891 (The Pile)

Max Activating Token Index: 653

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5062. Min Act: -0.0000

Data Index: 170875 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5435. Min Act: -0.0000

Data Index: 955679 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1564246 (The Pile)

Max Activating Token Index: 832

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1905590 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4980. Min Act: -0.0000

Data Index: 926316 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1895098 (The Pile)

Max Activating Token Index: 310

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4381. Min Act: -0.0000

Data Index: 250810 (The Pile)

Max Activating Token Index: 844

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4111. Min Act: -0.0000

Data Index: 1334430 (The Pile)

Max Activating Token Index: 934

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3998. Min Act: -0.0000

Data Index: 69050 (The Pile)

Max Activating Token Index: 464

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3973. Min Act: -0.0000

Data Index: 450250 (The Pile)

Max Activating Token Index: 104

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3747. Min Act: -0.0000

Data Index: 693229 (The Pile)

Max Activating Token Index: 92

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1319689 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1721627 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1898380 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3458. Min Act: -0.0000

Data Index: 790252 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1085364 (The Pile)

Max Activating Token Index: 347