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

Dataset: The Pile

Neuron 4537 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0817. Min Act: -0.0000

Data Index: 523471 (The Pile)

Max Activating Token Index: 26

Text #1

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0501. Min Act: -0.0000

Data Index: 371934 (The Pile)

Max Activating Token Index: 593

Text #2

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.3566. Min Act: -0.0000

Data Index: 621430 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0310. Min Act: -0.0000

Data Index: 420144 (The Pile)

Max Activating Token Index: 593

Text #4

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.1333. Min Act: -0.0000

Data Index: 967283 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.1263. Min Act: -0.0000

Data Index: 1772728 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0654. Min Act: -0.0000

Data Index: 1998861 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.1641. Min Act: -0.0000

Data Index: 17483 (The Pile)

Max Activating Token Index: 751

Text #8

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.8612. Min Act: -0.0000

Data Index: 658270 (The Pile)

Max Activating Token Index: 853

Text #9

Max Range: 3.3566. Min Range: -3.3566

Max Act: 3.0261. Min Act: -0.0000

Data Index: 1422545 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.9889. Min Act: -0.0000

Data Index: 1203189 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.6097. Min Act: -0.0000

Data Index: 329459 (The Pile)

Max Activating Token Index: 82

Text #12

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.7352. Min Act: -0.0000

Data Index: 476651 (The Pile)

Max Activating Token Index: 94

Text #13

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.7138. Min Act: -0.0000

Data Index: 634770 (The Pile)

Max Activating Token Index: 103

Text #14

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.5202. Min Act: -0.0000

Data Index: 82977 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.4522. Min Act: -0.0000

Data Index: 542614 (The Pile)

Max Activating Token Index: 976

Text #16

Max Range: 3.3566. Min Range: -3.3566

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1362997 (The Pile)

Max Activating Token Index: 269

Text #17

Max Range: 3.3566. Min Range: -3.3566

Max Act: 1.6842. Min Act: -0.0000

Data Index: 1207739 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 3.3566. Min Range: -3.3566

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1791868 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 3.3566. Min Range: -3.3566

Max Act: 1.5864. Min Act: -0.0000

Data Index: 1958308 (The Pile)

Max Activating Token Index: 745