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

Dataset: The Pile

Neuron 1272 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.9388. Min Act: -0.0000

Data Index: 1335258 (The Pile)

Max Activating Token Index: 29

Text #1

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.8405. Min Act: -0.0000

Data Index: 759013 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6506. Min Act: -0.0000

Data Index: 533063 (The Pile)

Max Activating Token Index: 303

Text #3

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5384. Min Act: -0.0000

Data Index: 1256508 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5529. Min Act: -0.0000

Data Index: 189068 (The Pile)

Max Activating Token Index: 32

Text #5

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6832. Min Act: -0.0000

Data Index: 29160 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5600. Min Act: -0.0000

Data Index: 1908838 (The Pile)

Max Activating Token Index: 453

Text #7

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4439. Min Act: -0.0000

Data Index: 1590485 (The Pile)

Max Activating Token Index: 56

Text #8

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4833. Min Act: -0.0000

Data Index: 1821067 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1363103 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4534. Min Act: -0.0000

Data Index: 819839 (The Pile)

Max Activating Token Index: 585

Text #11

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5371. Min Act: -0.0000

Data Index: 1380827 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4080. Min Act: -0.0000

Data Index: 1029896 (The Pile)

Max Activating Token Index: 541

Text #13

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4359. Min Act: -0.0000

Data Index: 355536 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1104782 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1917738 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.3882. Min Act: -0.0000

Data Index: 619831 (The Pile)

Max Activating Token Index: 536

Text #17

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.4165. Min Act: -0.0000

Data Index: 532368 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5073. Min Act: -0.0000

Data Index: 1212425 (The Pile)

Max Activating Token Index: 320

Text #19

Max Range: 1.9388. Min Range: -1.9388

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1388053 (The Pile)

Max Activating Token Index: 778