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

Dataset: The Pile

Neuron 4863 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: 1.4817. Min Range: -1.4817

Max Act: 1.4817. Min Act: -0.0000

Data Index: 1345808 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.3094. Min Act: -0.0000

Data Index: 511338 (The Pile)

Max Activating Token Index: 123

Text #2

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1549. Min Act: -0.0000

Data Index: 722610 (The Pile)

Max Activating Token Index: 105

Text #3

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1403. Min Act: -0.0000

Data Index: 621120 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1001. Min Act: -0.0000

Data Index: 1496734 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1977691 (The Pile)

Max Activating Token Index: 419

Text #6

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0949. Min Act: -0.0000

Data Index: 821734 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0531. Min Act: -0.0000

Data Index: 1298200 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0799. Min Act: -0.0000

Data Index: 689684 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0807. Min Act: -0.0000

Data Index: 734740 (The Pile)

Max Activating Token Index: 252

Text #10

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1680292 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0411. Min Act: -0.0000

Data Index: 1898027 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1326030 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1710506 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0349. Min Act: -0.0000

Data Index: 1119474 (The Pile)

Max Activating Token Index: 157

Text #15

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0138. Min Act: -0.0000

Data Index: 349953 (The Pile)

Max Activating Token Index: 218

Text #16

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.9019. Min Act: -0.0000

Data Index: 26721 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0351. Min Act: -0.0000

Data Index: 1146780 (The Pile)

Max Activating Token Index: 357

Text #18

Max Range: 1.4817. Min Range: -1.4817

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1341220 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.4817. Min Range: -1.4817

Max Act: 0.9753. Min Act: -0.0000

Data Index: 1942596 (The Pile)

Max Activating Token Index: 560