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

Dataset: The Pile

Neuron 2458 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: 5.0118. Min Range: -5.0118

Max Act: 4.8484. Min Act: -0.0000

Data Index: 150015 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 5.0118. Min Range: -5.0118

Max Act: 5.0118. Min Act: -0.0000

Data Index: 992662 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.7774. Min Act: -0.0000

Data Index: 1317348 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.3059. Min Act: -0.0000

Data Index: 92092 (The Pile)

Max Activating Token Index: 977

Text #4

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.3021. Min Act: -0.0000

Data Index: 1454846 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.3436. Min Act: -0.0000

Data Index: 1968382 (The Pile)

Max Activating Token Index: 254

Text #6

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.2642. Min Act: -0.0000

Data Index: 1577331 (The Pile)

Max Activating Token Index: 563

Text #7

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.7436. Min Act: -0.0000

Data Index: 146300 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.9929. Min Act: -0.0000

Data Index: 634322 (The Pile)

Max Activating Token Index: 370

Text #9

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.9469. Min Act: -0.0000

Data Index: 1495411 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.0873. Min Act: -0.0000

Data Index: 694053 (The Pile)

Max Activating Token Index: 285

Text #11

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.9122. Min Act: -0.0000

Data Index: 873579 (The Pile)

Max Activating Token Index: 698

Text #12

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.9382. Min Act: -0.0000

Data Index: 1549786 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.8901. Min Act: -0.0000

Data Index: 1596598 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.9202. Min Act: -0.0000

Data Index: 1562351 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.9387. Min Act: -0.0000

Data Index: 446434 (The Pile)

Max Activating Token Index: 171

Text #16

Max Range: 5.0118. Min Range: -5.0118

Max Act: 3.7576. Min Act: -0.0000

Data Index: 1036541 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.0750. Min Act: -0.0000

Data Index: 3364 (The Pile)

Max Activating Token Index: 148

Text #18

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.0503. Min Act: -0.0000

Data Index: 1917389 (The Pile)

Max Activating Token Index: 516

Text #19

Max Range: 5.0118. Min Range: -5.0118

Max Act: 4.0491. Min Act: -0.0000

Data Index: 99730 (The Pile)

Max Activating Token Index: 316