Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 1.1383. Min Range: -1.1383

Max Act: 1.1383. Min Act: -0.0000

Data Index: 1732167 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.9830. Min Act: -0.0000

Data Index: 519827 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.9693. Min Act: -0.0000

Data Index: 664499 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.9240. Min Act: -0.0000

Data Index: 622949 (The Pile)

Max Activating Token Index: 689

Text #4

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8892. Min Act: -0.0000

Data Index: 31494 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8694. Min Act: -0.0000

Data Index: 903381 (The Pile)

Max Activating Token Index: 816

Text #6

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8648. Min Act: -0.0000

Data Index: 487465 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8698. Min Act: -0.0000

Data Index: 1401848 (The Pile)

Max Activating Token Index: 761

Text #8

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8436. Min Act: -0.0000

Data Index: 213355 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1317351 (The Pile)

Max Activating Token Index: 1005

Text #10

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1314514 (The Pile)

Max Activating Token Index: 459

Text #11

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1444430 (The Pile)

Max Activating Token Index: 580

Text #12

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8093. Min Act: -0.0000

Data Index: 532850 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.8044. Min Act: -0.0000

Data Index: 380983 (The Pile)

Max Activating Token Index: 62

Text #14

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7441. Min Act: -0.0000

Data Index: 1105810 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7100. Min Act: -0.0000

Data Index: 952478 (The Pile)

Max Activating Token Index: 650

Text #16

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7509. Min Act: -0.0000

Data Index: 839906 (The Pile)

Max Activating Token Index: 885

Text #17

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.6660. Min Act: -0.0000

Data Index: 111758 (The Pile)

Max Activating Token Index: 493

Text #18

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.7005. Min Act: -0.0001

Data Index: 174001 (The Pile)

Max Activating Token Index: 786

Text #19

Max Range: 1.1383. Min Range: -1.1383

Max Act: 0.6970. Min Act: -0.0000

Data Index: 786246 (The Pile)

Max Activating Token Index: 647