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

Dataset: The Pile

Neuron 2866 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: 0.7112. Min Range: -0.7112

Max Act: 0.6879. Min Act: -0.0000

Data Index: 960132 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.7112. Min Act: -0.0000

Data Index: 895559 (The Pile)

Max Activating Token Index: 551

Text #2

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6590. Min Act: -0.0000

Data Index: 1399708 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6088. Min Act: -0.0000

Data Index: 72376 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6533. Min Act: -0.0000

Data Index: 1438419 (The Pile)

Max Activating Token Index: 495

Text #5

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6107. Min Act: -0.0000

Data Index: 368101 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1090570 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.6006. Min Act: -0.0000

Data Index: 376593 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5412. Min Act: -0.0000

Data Index: 1853032 (The Pile)

Max Activating Token Index: 940

Text #9

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5621. Min Act: -0.0000

Data Index: 811566 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5640. Min Act: 0.0000

Data Index: 470576 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.4686. Min Act: -0.0000

Data Index: 1420687 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1866046 (The Pile)

Max Activating Token Index: 588

Text #13

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5322. Min Act: -0.0000

Data Index: 998204 (The Pile)

Max Activating Token Index: 753

Text #14

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1768052 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5219. Min Act: 0.0000

Data Index: 644259 (The Pile)

Max Activating Token Index: 181

Text #16

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.4775. Min Act: -0.0000

Data Index: 1727080 (The Pile)

Max Activating Token Index: 958

Text #17

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1827689 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1075805 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 0.7112. Min Range: -0.7112

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1136194 (The Pile)

Max Activating Token Index: 179