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

Dataset: The Pile

Neuron 4656 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: 0.5689. Min Range: -0.5689

Max Act: 0.5689. Min Act: -0.0000

Data Index: 1255567 (The Pile)

Max Activating Token Index: 347

Text #1

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3806. Min Act: -0.0000

Data Index: 390922 (The Pile)

Max Activating Token Index: 956

Text #2

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1371474 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4336. Min Act: -0.0000

Data Index: 352806 (The Pile)

Max Activating Token Index: 727

Text #4

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.4027. Min Act: -0.0000

Data Index: 585882 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1970417 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3562. Min Act: -0.0000

Data Index: 292399 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3715. Min Act: -0.0000

Data Index: 304213 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3789. Min Act: -0.0000

Data Index: 1709480 (The Pile)

Max Activating Token Index: 587

Text #9

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3981. Min Act: -0.0000

Data Index: 584203 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3755. Min Act: -0.0000

Data Index: 934603 (The Pile)

Max Activating Token Index: 959

Text #11

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1327190 (The Pile)

Max Activating Token Index: 926

Text #12

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3675. Min Act: -0.0000

Data Index: 1444332 (The Pile)

Max Activating Token Index: 649

Text #13

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3909. Min Act: -0.0000

Data Index: 854658 (The Pile)

Max Activating Token Index: 985

Text #14

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3262. Min Act: -0.0000

Data Index: 1735801 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3717. Min Act: -0.0000

Data Index: 197792 (The Pile)

Max Activating Token Index: 813

Text #16

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1066780 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3517. Min Act: -0.0000

Data Index: 447363 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3431. Min Act: -0.0000

Data Index: 897460 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.5689. Min Range: -0.5689

Max Act: 0.3517. Min Act: -0.0000

Data Index: 378103 (The Pile)

Max Activating Token Index: 843