Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 381 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.7601. Min Act: -0.0000

Data Index: 703390 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.6098. Min Act: -0.0000

Data Index: 681545 (The Pile)

Max Activating Token Index: 435

Text #2

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1790937 (The Pile)

Max Activating Token Index: 313

Text #3

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.5424. Min Act: -0.0000

Data Index: 265995 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1829778 (The Pile)

Max Activating Token Index: 229

Text #5

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1527340 (The Pile)

Max Activating Token Index: 1004

Text #6

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4712. Min Act: -0.0000

Data Index: 811634 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1570437 (The Pile)

Max Activating Token Index: 1012

Text #8

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4109. Min Act: -0.0000

Data Index: 535995 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1966634 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1750581 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1964855 (The Pile)

Max Activating Token Index: 678

Text #12

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1567042 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1645629 (The Pile)

Max Activating Token Index: 662

Text #14

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4629. Min Act: -0.0000

Data Index: 90917 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1238731 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1550833 (The Pile)

Max Activating Token Index: 728

Text #17

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4803. Min Act: -0.0000

Data Index: 967930 (The Pile)

Max Activating Token Index: 98

Text #18

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4471. Min Act: -0.0000

Data Index: 1884847 (The Pile)

Max Activating Token Index: 195

Text #19

Max Range: 0.7601. Min Range: -0.7601

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1799089 (The Pile)

Max Activating Token Index: 277