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

Dataset: The Pile

Neuron 2959 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: 1.8564. Min Range: -1.8564

Max Act: 1.8564. Min Act: -0.0000

Data Index: 706755 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.5851. Min Act: -0.0000

Data Index: 433091 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.5618. Min Act: -0.0000

Data Index: 242358 (The Pile)

Max Activating Token Index: 650

Text #3

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.5457. Min Act: -0.0000

Data Index: 1650942 (The Pile)

Max Activating Token Index: 197

Text #4

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4418. Min Act: -0.0000

Data Index: 947586 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4975. Min Act: -0.0000

Data Index: 1951082 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1476175 (The Pile)

Max Activating Token Index: 792

Text #7

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.5667. Min Act: -0.0000

Data Index: 1369653 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4753. Min Act: -0.0000

Data Index: 1584673 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.3736. Min Act: -0.0000

Data Index: 635858 (The Pile)

Max Activating Token Index: 193

Text #10

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.3690. Min Act: -0.0000

Data Index: 1774160 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4461. Min Act: -0.0000

Data Index: 101138 (The Pile)

Max Activating Token Index: 281

Text #12

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4191. Min Act: -0.0000

Data Index: 1906960 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.5516. Min Act: -0.0000

Data Index: 1585845 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1943656 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.3837. Min Act: -0.0000

Data Index: 441638 (The Pile)

Max Activating Token Index: 219

Text #16

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.6048. Min Act: -0.0000

Data Index: 482603 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.5022. Min Act: -0.0000

Data Index: 906012 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.3570. Min Act: -0.0000

Data Index: 1445626 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 1.8564. Min Range: -1.8564

Max Act: 1.4089. Min Act: -0.0000

Data Index: 1095832 (The Pile)

Max Activating Token Index: 61