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

Dataset: The Pile

Neuron 4112 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: 1.4633. Min Range: -1.4633

Max Act: 1.4440. Min Act: -0.0000

Data Index: 801351 (The Pile)

Max Activating Token Index: 370

Text #1

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.4633. Min Act: -0.0000

Data Index: 1408400 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 1.4633. Min Range: -1.4633

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1809744 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.9717. Min Act: -0.0000

Data Index: 566398 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1978165 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.8626. Min Act: -0.0000

Data Index: 331540 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.5855. Min Act: -0.0000

Data Index: 197014 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.5896. Min Act: -0.0000

Data Index: 72477 (The Pile)

Max Activating Token Index: 164

Text #8

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.6290. Min Act: 0.0000

Data Index: 497505 (The Pile)

Max Activating Token Index: 282

Text #9

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1309090 (The Pile)

Max Activating Token Index: 172

Text #10

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1245293 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.5167. Min Act: 0.0000

Data Index: 290509 (The Pile)

Max Activating Token Index: 290

Text #12

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.5020. Min Act: -0.0000

Data Index: 1333390 (The Pile)

Max Activating Token Index: 885

Text #13

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.4921. Min Act: -0.0000

Data Index: 1418133 (The Pile)

Max Activating Token Index: 267

Text #14

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.5074. Min Act: 0.0000

Data Index: 1476947 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1084665 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.4993. Min Act: -0.0000

Data Index: 634206 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.4814. Min Act: -0.0000

Data Index: 892391 (The Pile)

Max Activating Token Index: 707

Text #18

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.4800. Min Act: -0.0000

Data Index: 905506 (The Pile)

Max Activating Token Index: 673

Text #19

Max Range: 1.4633. Min Range: -1.4633

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1099812 (The Pile)

Max Activating Token Index: 992