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

Dataset: The Pile

Neuron 3292 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.4391. Min Act: -0.0000

Data Index: 412712 (The Pile)

Max Activating Token Index: 450

Text #1

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2903. Min Act: -0.0000

Data Index: 1336539 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1800493 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2246. Min Act: -0.0000

Data Index: 19501 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.2202. Min Act: -0.0000

Data Index: 235963 (The Pile)

Max Activating Token Index: 986

Text #5

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1024402 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1833482 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1763. Min Act: -0.0000

Data Index: 107574 (The Pile)

Max Activating Token Index: 682

Text #8

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1864. Min Act: -0.0000

Data Index: 18436 (The Pile)

Max Activating Token Index: 873

Text #9

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1907. Min Act: -0.0000

Data Index: 968516 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1956563 (The Pile)

Max Activating Token Index: 380

Text #11

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1753. Min Act: -0.0000

Data Index: 211150 (The Pile)

Max Activating Token Index: 1003

Text #12

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1774. Min Act: -0.0000

Data Index: 428233 (The Pile)

Max Activating Token Index: 992

Text #13

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1721. Min Act: -0.0000

Data Index: 1970292 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1805168 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1644. Min Act: -0.0000

Data Index: 334636 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1488. Min Act: -0.0000

Data Index: 1366611 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1572. Min Act: -0.0000

Data Index: 329890 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1718556 (The Pile)

Max Activating Token Index: 685

Text #19

Max Range: 0.4391. Min Range: -0.4391

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1350379 (The Pile)

Max Activating Token Index: 975