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

Dataset: The Pile

Neuron 3561 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: 0.8106. Min Range: -0.8106

Max Act: 0.8091. Min Act: -0.0000

Data Index: 55668 (The Pile)

Max Activating Token Index: 321

Text #1

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.8106. Min Act: -0.0000

Data Index: 848893 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.7937. Min Act: -0.0000

Data Index: 733672 (The Pile)

Max Activating Token Index: 439

Text #3

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1613271 (The Pile)

Max Activating Token Index: 630

Text #4

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5826. Min Act: -0.0000

Data Index: 449405 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1255536 (The Pile)

Max Activating Token Index: 126

Text #6

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1759160 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5521. Min Act: -0.0000

Data Index: 634846 (The Pile)

Max Activating Token Index: 713

Text #8

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1279295 (The Pile)

Max Activating Token Index: 555

Text #9

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1296303 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5536. Min Act: -0.0000

Data Index: 137096 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5494. Min Act: -0.0000

Data Index: 998327 (The Pile)

Max Activating Token Index: 567

Text #12

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4879. Min Act: -0.0000

Data Index: 883615 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5457. Min Act: -0.0000

Data Index: 237647 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5553. Min Act: -0.0000

Data Index: 95922 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1842755 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5368. Min Act: -0.0000

Data Index: 700912 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5577. Min Act: -0.0000

Data Index: 107024 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.4992. Min Act: -0.0000

Data Index: 38462 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 0.8106. Min Range: -0.8106

Max Act: 0.5185. Min Act: -0.0000

Data Index: 804949 (The Pile)

Max Activating Token Index: 966