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

Dataset: The Pile

Neuron 3822 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.7356. Min Act: -0.0000

Data Index: 587380 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.2718. Min Act: -0.0000

Data Index: 753800 (The Pile)

Max Activating Token Index: 629

Text #2

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.0733. Min Act: -0.0000

Data Index: 1304497 (The Pile)

Max Activating Token Index: 493

Text #3

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.0663. Min Act: -0.0000

Data Index: 500539 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1045929 (The Pile)

Max Activating Token Index: 585

Text #5

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1147309 (The Pile)

Max Activating Token Index: 917

Text #6

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9457. Min Act: 0.0000

Data Index: 884767 (The Pile)

Max Activating Token Index: 481

Text #7

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9890. Min Act: -0.0000

Data Index: 84122 (The Pile)

Max Activating Token Index: 932

Text #8

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9265. Min Act: -0.0000

Data Index: 1576336 (The Pile)

Max Activating Token Index: 937

Text #9

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9562. Min Act: -0.0000

Data Index: 329083 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9562. Min Act: -0.0000

Data Index: 123511 (The Pile)

Max Activating Token Index: 892

Text #11

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9654. Min Act: -0.0000

Data Index: 932604 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.7356. Min Range: -1.7356

Max Act: 1.0029. Min Act: 0.0000

Data Index: 1485554 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1306378 (The Pile)

Max Activating Token Index: 355

Text #14

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9237. Min Act: 0.0000

Data Index: 1928503 (The Pile)

Max Activating Token Index: 168

Text #15

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9133. Min Act: -0.0000

Data Index: 967385 (The Pile)

Max Activating Token Index: 506

Text #16

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.8961. Min Act: 0.0000

Data Index: 1657427 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1147473 (The Pile)

Max Activating Token Index: 134

Text #18

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.7794. Min Act: -0.0000

Data Index: 555464 (The Pile)

Max Activating Token Index: 804

Text #19

Max Range: 1.7356. Min Range: -1.7356

Max Act: 0.8350. Min Act: 0.0000

Data Index: 1608039 (The Pile)

Max Activating Token Index: 893