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

Dataset: The Pile

Neuron 1192 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: 0.3836. Min Range: -0.3836

Max Act: 0.3836. Min Act: -0.0000

Data Index: 1042607 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1216789 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1213245 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3708. Min Act: -0.0000

Data Index: 715278 (The Pile)

Max Activating Token Index: 117

Text #4

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3488. Min Act: -0.0000

Data Index: 925114 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3549. Min Act: -0.0000

Data Index: 805570 (The Pile)

Max Activating Token Index: 408

Text #6

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3459. Min Act: -0.0000

Data Index: 1013742 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3477. Min Act: -0.0000

Data Index: 863326 (The Pile)

Max Activating Token Index: 133

Text #8

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1025100 (The Pile)

Max Activating Token Index: 177

Text #9

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3470. Min Act: -0.0000

Data Index: 283150 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3354. Min Act: -0.0000

Data Index: 693373 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1513739 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3277. Min Act: -0.0000

Data Index: 642939 (The Pile)

Max Activating Token Index: 472

Text #13

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3050. Min Act: -0.0000

Data Index: 316097 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3349. Min Act: -0.0000

Data Index: 589332 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1304007 (The Pile)

Max Activating Token Index: 215

Text #16

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2875. Min Act: -0.0000

Data Index: 1221871 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1095281 (The Pile)

Max Activating Token Index: 61

Text #18

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3010. Min Act: -0.0000

Data Index: 152508 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1976571 (The Pile)

Max Activating Token Index: 246