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

Dataset: The Pile

Neuron 3393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4728. Min Act: -0.0000

Data Index: 760759 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4577. Min Act: -0.0000

Data Index: 443595 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1535851 (The Pile)

Max Activating Token Index: 589

Text #3

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1382056 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4565. Min Act: -0.0000

Data Index: 957976 (The Pile)

Max Activating Token Index: 731

Text #5

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4057. Min Act: -0.0000

Data Index: 1941556 (The Pile)

Max Activating Token Index: 280

Text #6

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4300. Min Act: -0.0000

Data Index: 1203727 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1493458 (The Pile)

Max Activating Token Index: 863

Text #8

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4783. Min Act: -0.0000

Data Index: 644132 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3874. Min Act: -0.0000

Data Index: 872801 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4366. Min Act: -0.0000

Data Index: 252680 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3999. Min Act: -0.0000

Data Index: 643372 (The Pile)

Max Activating Token Index: 260

Text #12

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3929. Min Act: -0.0000

Data Index: 1657723 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4089. Min Act: -0.0000

Data Index: 789055 (The Pile)

Max Activating Token Index: 373

Text #14

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1564226 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4398. Min Act: -0.0000

Data Index: 577058 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1340383 (The Pile)

Max Activating Token Index: 940

Text #17

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.3879. Min Act: -0.0000

Data Index: 411547 (The Pile)

Max Activating Token Index: 668

Text #18

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4053. Min Act: -0.0000

Data Index: 63776 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.4783. Min Range: -0.4783

Max Act: 0.4147. Min Act: -0.0000

Data Index: 511613 (The Pile)

Max Activating Token Index: 959