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

Dataset: The Pile

Neuron 509 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: 0.9552. Min Range: -0.9552

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1924295 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1888494 (The Pile)

Max Activating Token Index: 7

Text #2

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7607. Min Act: -0.0000

Data Index: 589316 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1933837 (The Pile)

Max Activating Token Index: 282

Text #4

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8174. Min Act: -0.0000

Data Index: 1181974 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8660. Min Act: -0.0000

Data Index: 1766269 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8749. Min Act: -0.0000

Data Index: 1321224 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.9102. Min Act: -0.0000

Data Index: 845600 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1406412 (The Pile)

Max Activating Token Index: 17

Text #9

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7727. Min Act: -0.0000

Data Index: 605950 (The Pile)

Max Activating Token Index: 637

Text #10

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.6937. Min Act: -0.0000

Data Index: 34024 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1888503 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7382. Min Act: -0.0000

Data Index: 1728330 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.8219. Min Act: -0.0000

Data Index: 841591 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7657. Min Act: -0.0000

Data Index: 451663 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7442. Min Act: -0.0000

Data Index: 172396 (The Pile)

Max Activating Token Index: 670

Text #16

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7843. Min Act: -0.0000

Data Index: 1792864 (The Pile)

Max Activating Token Index: 87

Text #17

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1014161 (The Pile)

Max Activating Token Index: 173

Text #18

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7930. Min Act: -0.0000

Data Index: 1824557 (The Pile)

Max Activating Token Index: 90

Text #19

Max Range: 0.9552. Min Range: -0.9552

Max Act: 0.7420. Min Act: -0.0000

Data Index: 958206 (The Pile)

Max Activating Token Index: 40