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

Dataset: The Pile

Neuron 3237 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: 5.8768. Min Range: -5.8768

Max Act: 5.6616. Min Act: -0.0000

Data Index: 58436 (The Pile)

Max Activating Token Index: 561

Text #1

Max Range: 5.8768. Min Range: -5.8768

Max Act: 5.8768. Min Act: -0.0000

Data Index: 476393 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 5.8768. Min Range: -5.8768

Max Act: 5.4697. Min Act: -0.0000

Data Index: 1200058 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.8559. Min Act: -0.0000

Data Index: 685438 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.8771. Min Act: -0.0000

Data Index: 1714723 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.3175. Min Act: -0.0000

Data Index: 1296676 (The Pile)

Max Activating Token Index: 674

Text #6

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.6404. Min Act: -0.0000

Data Index: 1999069 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.1451. Min Act: -0.0000

Data Index: 1726432 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.6726. Min Act: -0.0000

Data Index: 720407 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.4662. Min Act: -0.0000

Data Index: 1193734 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.2380. Min Act: -0.0000

Data Index: 793187 (The Pile)

Max Activating Token Index: 685

Text #11

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.4599. Min Act: -0.0000

Data Index: 1109983 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.2372. Min Act: -0.0000

Data Index: 1362987 (The Pile)

Max Activating Token Index: 194

Text #13

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.2214. Min Act: -0.0000

Data Index: 1912113 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.2167. Min Act: -0.0000

Data Index: 1184637 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 5.8768. Min Range: -5.8768

Max Act: 3.8852. Min Act: -0.0000

Data Index: 887571 (The Pile)

Max Activating Token Index: 922

Text #16

Max Range: 5.8768. Min Range: -5.8768

Max Act: 4.0645. Min Act: -0.0000

Data Index: 251853 (The Pile)

Max Activating Token Index: 374

Text #17

Max Range: 5.8768. Min Range: -5.8768

Max Act: 3.5413. Min Act: -0.0000

Data Index: 1042088 (The Pile)

Max Activating Token Index: 914

Text #18

Max Range: 5.8768. Min Range: -5.8768

Max Act: 3.6580. Min Act: -0.0000

Data Index: 92721 (The Pile)

Max Activating Token Index: 248

Text #19

Max Range: 5.8768. Min Range: -5.8768

Max Act: 3.8864. Min Act: -0.0000

Data Index: 149948 (The Pile)

Max Activating Token Index: 659