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

Dataset: The Pile

Neuron 3918 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0718. Min Act: -0.0000

Data Index: 991271 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0678. Min Act: -0.0000

Data Index: 710849 (The Pile)

Max Activating Token Index: 532

Text #2

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1477521 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1559706 (The Pile)

Max Activating Token Index: 29

Text #4

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1520208 (The Pile)

Max Activating Token Index: 864

Text #5

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1018595 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0656. Min Act: -0.0000

Data Index: 551401 (The Pile)

Max Activating Token Index: 457

Text #7

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1051720 (The Pile)

Max Activating Token Index: 39

Text #8

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1868539 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1368107 (The Pile)

Max Activating Token Index: 782

Text #10

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1408957 (The Pile)

Max Activating Token Index: 210

Text #11

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0596. Min Act: -0.0000

Data Index: 347730 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0576. Min Act: -0.0000

Data Index: 1677266 (The Pile)

Max Activating Token Index: 560

Text #13

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0568. Min Act: -0.0000

Data Index: 584297 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1236080 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0625. Min Act: -0.0000

Data Index: 1608759 (The Pile)

Max Activating Token Index: 770

Text #16

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0569. Min Act: -0.0000

Data Index: 839646 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0588. Min Act: -0.0000

Data Index: 1328002 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1581083 (The Pile)

Max Activating Token Index: 276

Text #19

Max Range: 0.0726. Min Range: -0.0726

Max Act: 0.0520. Min Act: -0.0000

Data Index: 783374 (The Pile)

Max Activating Token Index: 1004