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

Dataset: The Pile

Neuron 3318 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.7155. Min Act: -0.0000

Data Index: 351190 (The Pile)

Max Activating Token Index: 957

Text #1

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.6188. Min Act: -0.0000

Data Index: 1601310 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1474164 (The Pile)

Max Activating Token Index: 944

Text #3

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5966. Min Act: -0.0000

Data Index: 158351 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5888. Min Act: -0.0000

Data Index: 291618 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5890. Min Act: -0.0000

Data Index: 617932 (The Pile)

Max Activating Token Index: 50

Text #6

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5700. Min Act: -0.0000

Data Index: 814591 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5635. Min Act: -0.0000

Data Index: 481378 (The Pile)

Max Activating Token Index: 372

Text #8

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5806. Min Act: -0.0000

Data Index: 1179447 (The Pile)

Max Activating Token Index: 726

Text #9

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5256. Min Act: -0.0000

Data Index: 322406 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1228642 (The Pile)

Max Activating Token Index: 442

Text #11

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5721. Min Act: -0.0000

Data Index: 954188 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.4954. Min Act: -0.0000

Data Index: 1814126 (The Pile)

Max Activating Token Index: 961

Text #13

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5480. Min Act: -0.0000

Data Index: 22424 (The Pile)

Max Activating Token Index: 328

Text #14

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1045178 (The Pile)

Max Activating Token Index: 220

Text #15

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1911096 (The Pile)

Max Activating Token Index: 435

Text #16

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5305. Min Act: -0.0000

Data Index: 900388 (The Pile)

Max Activating Token Index: 335

Text #17

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5467. Min Act: -0.0000

Data Index: 839258 (The Pile)

Max Activating Token Index: 766

Text #18

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5342. Min Act: -0.0000

Data Index: 321440 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.7155. Min Range: -0.7155

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1547920 (The Pile)

Max Activating Token Index: 398