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

Dataset: The Pile

Neuron 3433 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: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0000

Data Index: 923301 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0693. Min Act: -0.0000

Data Index: 999698 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0757. Min Act: -0.0000

Data Index: 647487 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0789. Min Act: -0.0000

Data Index: 380024 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1857453 (The Pile)

Max Activating Token Index: 447

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0686. Min Act: -0.0000

Data Index: 999183 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1104200 (The Pile)

Max Activating Token Index: 400

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0685. Min Act: -0.0000

Data Index: 1820279 (The Pile)

Max Activating Token Index: 369

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0647. Min Act: -0.0000

Data Index: 666703 (The Pile)

Max Activating Token Index: 657

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0643. Min Act: -0.0000

Data Index: 89075 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0583. Min Act: -0.0000

Data Index: 652147 (The Pile)

Max Activating Token Index: 349

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1340587 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1669583 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0571. Min Act: -0.0000

Data Index: 1276899 (The Pile)

Max Activating Token Index: 707

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0632. Min Act: -0.0000

Data Index: 768664 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0607. Min Act: -0.0000

Data Index: 196792 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0620. Min Act: -0.0000

Data Index: 1255638 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0554. Min Act: -0.0000

Data Index: 127245 (The Pile)

Max Activating Token Index: 229

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0617. Min Act: -0.0000

Data Index: 305863 (The Pile)

Max Activating Token Index: 299

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0530. Min Act: -0.0000

Data Index: 619310 (The Pile)

Max Activating Token Index: 223