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

Dataset: The Pile

Neuron 1664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7137. Min Range: -5.7137

Max Act: 5.7137. Min Act: -0.0000

Data Index: 1745280 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.7146. Min Act: -0.0000

Data Index: 26416 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 5.7137. Min Range: -5.7137

Max Act: 5.4086. Min Act: -0.0000

Data Index: 1864355 (The Pile)

Max Activating Token Index: 474

Text #3

Max Range: 5.7137. Min Range: -5.7137

Max Act: 5.1920. Min Act: -0.0000

Data Index: 176707 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.5583. Min Act: -0.0000

Data Index: 1469926 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 5.7137. Min Range: -5.7137

Max Act: 3.8951. Min Act: -0.0000

Data Index: 738740 (The Pile)

Max Activating Token Index: 842

Text #6

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.0632. Min Act: -0.0001

Data Index: 816886 (The Pile)

Max Activating Token Index: 690

Text #7

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.1917. Min Act: -0.0000

Data Index: 591790 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.0378. Min Act: -0.0000

Data Index: 1658039 (The Pile)

Max Activating Token Index: 134

Text #9

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.1778. Min Act: -0.0000

Data Index: 397312 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.1500. Min Act: -0.0000

Data Index: 505302 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.0507. Min Act: -0.0000

Data Index: 1152953 (The Pile)

Max Activating Token Index: 718

Text #12

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.0437. Min Act: -0.0000

Data Index: 544707 (The Pile)

Max Activating Token Index: 479

Text #13

Max Range: 5.7137. Min Range: -5.7137

Max Act: 3.8376. Min Act: -0.0001

Data Index: 1755166 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 5.7137. Min Range: -5.7137

Max Act: 2.9353. Min Act: -0.0000

Data Index: 296087 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 5.7137. Min Range: -5.7137

Max Act: 4.1120. Min Act: -0.0001

Data Index: 1520449 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 5.7137. Min Range: -5.7137

Max Act: 3.9387. Min Act: -0.0000

Data Index: 859956 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 5.7137. Min Range: -5.7137

Max Act: 3.9593. Min Act: -0.0000

Data Index: 276924 (The Pile)

Max Activating Token Index: 164

Text #18

Max Range: 5.7137. Min Range: -5.7137

Max Act: 3.7559. Min Act: -0.0000

Data Index: 1012570 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 5.7137. Min Range: -5.7137

Max Act: 3.8941. Min Act: -0.0000

Data Index: 819474 (The Pile)

Max Activating Token Index: 553