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

Dataset: The Pile

Neuron 4262 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1098333 (The Pile)

Max Activating Token Index: 308

Text #1

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.8691. Min Act: -0.0000

Data Index: 190118 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1928976 (The Pile)

Max Activating Token Index: 701

Text #3

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5434. Min Act: -0.0000

Data Index: 339913 (The Pile)

Max Activating Token Index: 924

Text #4

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5726. Min Act: -0.0000

Data Index: 412976 (The Pile)

Max Activating Token Index: 722

Text #5

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5409. Min Act: -0.0000

Data Index: 161581 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5342. Min Act: -0.0000

Data Index: 1495016 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.5260. Min Act: -0.0000

Data Index: 878996 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1000028 (The Pile)

Max Activating Token Index: 266

Text #9

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1780276 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1788593 (The Pile)

Max Activating Token Index: 931

Text #11

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4625. Min Act: -0.0000

Data Index: 1758855 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4103. Min Act: -0.0000

Data Index: 1612305 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4394. Min Act: -0.0000

Data Index: 1000688 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4462. Min Act: -0.0000

Data Index: 1774380 (The Pile)

Max Activating Token Index: 837

Text #15

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1316860 (The Pile)

Max Activating Token Index: 304

Text #16

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4398. Min Act: -0.0000

Data Index: 218750 (The Pile)

Max Activating Token Index: 864

Text #17

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1668467 (The Pile)

Max Activating Token Index: 962

Text #18

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1026615 (The Pile)

Max Activating Token Index: 391

Text #19

Max Range: 0.8966. Min Range: -0.8966

Max Act: 0.4067. Min Act: -0.0000

Data Index: 697457 (The Pile)

Max Activating Token Index: 984