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

Dataset: The Pile

Neuron 2035 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: 0.8824. Min Range: -0.8824

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1502161 (The Pile)

Max Activating Token Index: 706

Text #1

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8824. Min Act: -0.0000

Data Index: 430434 (The Pile)

Max Activating Token Index: 633

Text #2

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8117. Min Act: -0.0000

Data Index: 175638 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.8337. Min Act: -0.0000

Data Index: 130168 (The Pile)

Max Activating Token Index: 331

Text #4

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7932. Min Act: -0.0000

Data Index: 1519056 (The Pile)

Max Activating Token Index: 397

Text #5

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1401025 (The Pile)

Max Activating Token Index: 348

Text #6

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7109. Min Act: -0.0000

Data Index: 316523 (The Pile)

Max Activating Token Index: 680

Text #7

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1435627 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1682242 (The Pile)

Max Activating Token Index: 694

Text #9

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7079. Min Act: -0.0000

Data Index: 615067 (The Pile)

Max Activating Token Index: 780

Text #10

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6959. Min Act: -0.0000

Data Index: 587243 (The Pile)

Max Activating Token Index: 389

Text #11

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.7075. Min Act: -0.0000

Data Index: 716034 (The Pile)

Max Activating Token Index: 737

Text #12

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6868. Min Act: -0.0000

Data Index: 369934 (The Pile)

Max Activating Token Index: 984

Text #13

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1911677 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6895. Min Act: -0.0000

Data Index: 244313 (The Pile)

Max Activating Token Index: 468

Text #15

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6400. Min Act: -0.0000

Data Index: 762803 (The Pile)

Max Activating Token Index: 692

Text #16

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1746208 (The Pile)

Max Activating Token Index: 644

Text #17

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1552035 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.6474. Min Act: -0.0000

Data Index: 1824974 (The Pile)

Max Activating Token Index: 522

Text #19

Max Range: 0.8824. Min Range: -0.8824

Max Act: 0.5876. Min Act: -0.0000

Data Index: 1954491 (The Pile)

Max Activating Token Index: 457