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

Dataset: The Pile

Neuron 4774 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: 0.6732. Min Range: -0.6732

Max Act: 0.6732. Min Act: -0.0000

Data Index: 119197 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1584793 (The Pile)

Max Activating Token Index: 178

Text #2

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6249. Min Act: -0.0000

Data Index: 301452 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6601. Min Act: -0.0000

Data Index: 723620 (The Pile)

Max Activating Token Index: 270

Text #4

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5945. Min Act: -0.0000

Data Index: 420683 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6030. Min Act: -0.0000

Data Index: 606082 (The Pile)

Max Activating Token Index: 47

Text #6

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6229. Min Act: -0.0000

Data Index: 159860 (The Pile)

Max Activating Token Index: 536

Text #7

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6195. Min Act: -0.0000

Data Index: 238190 (The Pile)

Max Activating Token Index: 131

Text #8

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6019. Min Act: -0.0000

Data Index: 1962979 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6006. Min Act: -0.0000

Data Index: 394896 (The Pile)

Max Activating Token Index: 90

Text #10

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6149. Min Act: -0.0000

Data Index: 362523 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5787. Min Act: -0.0000

Data Index: 1342230 (The Pile)

Max Activating Token Index: 167

Text #12

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1024160 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5795. Min Act: -0.0000

Data Index: 163163 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5797. Min Act: -0.0000

Data Index: 802456 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5748. Min Act: -0.0000

Data Index: 52846 (The Pile)

Max Activating Token Index: 104

Text #16

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1800892 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5559. Min Act: -0.0000

Data Index: 843026 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1951949 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5542. Min Act: -0.0000

Data Index: 105284 (The Pile)

Max Activating Token Index: 594