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

Dataset: The Pile

Neuron 663 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: 3.2681. Min Range: -3.2681

Max Act: 3.2438. Min Act: -0.0000

Data Index: 707302 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 3.2681. Min Range: -3.2681

Max Act: 3.2681. Min Act: -0.0000

Data Index: 1998117 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 3.2681. Min Range: -3.2681

Max Act: 3.1206. Min Act: -0.0000

Data Index: 787630 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.9537. Min Act: -0.0000

Data Index: 513753 (The Pile)

Max Activating Token Index: 588

Text #4

Max Range: 3.2681. Min Range: -3.2681

Max Act: 3.0626. Min Act: -0.0000

Data Index: 610827 (The Pile)

Max Activating Token Index: 773

Text #5

Max Range: 3.2681. Min Range: -3.2681

Max Act: 3.0801. Min Act: -0.0000

Data Index: 1464377 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.7689. Min Act: -0.0000

Data Index: 1639075 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.9696. Min Act: -0.0000

Data Index: 1713278 (The Pile)

Max Activating Token Index: 471

Text #8

Max Range: 3.2681. Min Range: -3.2681

Max Act: 3.1086. Min Act: -0.0000

Data Index: 1404322 (The Pile)

Max Activating Token Index: 461

Text #9

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.9246. Min Act: -0.0000

Data Index: 1748692 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.7580. Min Act: -0.0000

Data Index: 1443525 (The Pile)

Max Activating Token Index: 786

Text #11

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.8905. Min Act: -0.0000

Data Index: 1775082 (The Pile)

Max Activating Token Index: 285

Text #12

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.8727. Min Act: -0.0000

Data Index: 1231628 (The Pile)

Max Activating Token Index: 274

Text #13

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.7283. Min Act: -0.0000

Data Index: 448907 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.8434. Min Act: -0.0000

Data Index: 1866145 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.9373. Min Act: -0.0000

Data Index: 1037330 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.9704. Min Act: -0.0000

Data Index: 1362565 (The Pile)

Max Activating Token Index: 990

Text #17

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.8187. Min Act: -0.0000

Data Index: 1361960 (The Pile)

Max Activating Token Index: 94

Text #18

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.7930. Min Act: -0.0000

Data Index: 1636136 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 3.2681. Min Range: -3.2681

Max Act: 2.7815. Min Act: -0.0000

Data Index: 920965 (The Pile)

Max Activating Token Index: 557