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

Dataset: The Pile

Neuron 1628 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: 0.5625. Min Range: -0.5625

Max Act: 0.5625. Min Act: -0.0000

Data Index: 327302 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4069. Min Act: -0.0000

Data Index: 330116 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3949. Min Act: -0.0000

Data Index: 388830 (The Pile)

Max Activating Token Index: 263

Text #3

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.4167. Min Act: -0.0000

Data Index: 1344135 (The Pile)

Max Activating Token Index: 253

Text #4

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3387. Min Act: -0.0000

Data Index: 598147 (The Pile)

Max Activating Token Index: 767

Text #5

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1043139 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3591. Min Act: -0.0000

Data Index: 247265 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3304. Min Act: -0.0000

Data Index: 1622766 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1333650 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1626639 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3691. Min Act: -0.0000

Data Index: 1800601 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3483. Min Act: -0.0000

Data Index: 483121 (The Pile)

Max Activating Token Index: 649

Text #12

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3436. Min Act: -0.0000

Data Index: 1569514 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3295. Min Act: -0.0000

Data Index: 1052986 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3499. Min Act: -0.0000

Data Index: 762806 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3133. Min Act: -0.0000

Data Index: 1597944 (The Pile)

Max Activating Token Index: 439

Text #16

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1912889 (The Pile)

Max Activating Token Index: 669

Text #17

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3587. Min Act: -0.0000

Data Index: 981473 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1176571 (The Pile)

Max Activating Token Index: 945

Text #19

Max Range: 0.5625. Min Range: -0.5625

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1701239 (The Pile)

Max Activating Token Index: 604