Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2697 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.7126. Min Act: -0.0000

Data Index: 294741 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.6398. Min Act: -0.0000

Data Index: 424789 (The Pile)

Max Activating Token Index: 307

Text #2

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.2012. Min Act: -0.0000

Data Index: 792365 (The Pile)

Max Activating Token Index: 287

Text #3

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.3196. Min Act: -0.0000

Data Index: 448941 (The Pile)

Max Activating Token Index: 438

Text #4

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.4606. Min Act: -0.0000

Data Index: 998851 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.2328. Min Act: -0.0000

Data Index: 539734 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 3.7126. Min Range: -3.7126

Max Act: 2.8978. Min Act: -0.0000

Data Index: 988625 (The Pile)

Max Activating Token Index: 57

Text #7

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.0331. Min Act: -0.0000

Data Index: 847420 (The Pile)

Max Activating Token Index: 727

Text #8

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.2980. Min Act: -0.0000

Data Index: 571795 (The Pile)

Max Activating Token Index: 285

Text #9

Max Range: 3.7126. Min Range: -3.7126

Max Act: 2.9797. Min Act: -0.0000

Data Index: 1500765 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.0959. Min Act: -0.0000

Data Index: 1115991 (The Pile)

Max Activating Token Index: 291

Text #11

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.0664. Min Act: -0.0000

Data Index: 1707054 (The Pile)

Max Activating Token Index: 521

Text #12

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.0064. Min Act: -0.0000

Data Index: 1920845 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.0389. Min Act: -0.0000

Data Index: 1808115 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.1519. Min Act: -0.0000

Data Index: 768948 (The Pile)

Max Activating Token Index: 176

Text #15

Max Range: 3.7126. Min Range: -3.7126

Max Act: 2.8385. Min Act: -0.0000

Data Index: 648757 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 3.7126. Min Range: -3.7126

Max Act: 2.9747. Min Act: -0.0000

Data Index: 252364 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 3.7126. Min Range: -3.7126

Max Act: 3.2572. Min Act: -0.0000

Data Index: 1087423 (The Pile)

Max Activating Token Index: 679

Text #18

Max Range: 3.7126. Min Range: -3.7126

Max Act: 2.9649. Min Act: -0.0000

Data Index: 1011906 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 3.7126. Min Range: -3.7126

Max Act: 2.6970. Min Act: -0.0000

Data Index: 905721 (The Pile)

Max Activating Token Index: 824