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

Dataset: The Pile

Neuron 4617 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: 3.9038. Min Range: -3.9038

Max Act: 3.9038. Min Act: -0.0000

Data Index: 224630 (The Pile)

Max Activating Token Index: 735

Text #1

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.8354. Min Act: -0.0000

Data Index: 1992017 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.7998. Min Act: -0.0000

Data Index: 1263179 (The Pile)

Max Activating Token Index: 744

Text #3

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.5772. Min Act: -0.0000

Data Index: 699876 (The Pile)

Max Activating Token Index: 271

Text #4

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.5155. Min Act: -0.0000

Data Index: 464349 (The Pile)

Max Activating Token Index: 346

Text #5

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.2284. Min Act: -0.0000

Data Index: 1515761 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.1140. Min Act: -0.0000

Data Index: 417577 (The Pile)

Max Activating Token Index: 275

Text #7

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9512. Min Act: -0.0000

Data Index: 165154 (The Pile)

Max Activating Token Index: 1008

Text #8

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9287. Min Act: -0.0000

Data Index: 1239059 (The Pile)

Max Activating Token Index: 59

Text #9

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.0949. Min Act: -0.0000

Data Index: 1040793 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.0388. Min Act: -0.0000

Data Index: 1738145 (The Pile)

Max Activating Token Index: 55

Text #11

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9858. Min Act: -0.0000

Data Index: 1462617 (The Pile)

Max Activating Token Index: 446

Text #12

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9692. Min Act: -0.0000

Data Index: 1468396 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 3.9038. Min Range: -3.9038

Max Act: 3.0939. Min Act: -0.0000

Data Index: 352568 (The Pile)

Max Activating Token Index: 519

Text #14

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9786. Min Act: -0.0000

Data Index: 962751 (The Pile)

Max Activating Token Index: 850

Text #15

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9277. Min Act: -0.0000

Data Index: 918545 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9383. Min Act: -0.0000

Data Index: 111118 (The Pile)

Max Activating Token Index: 143

Text #17

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.7905. Min Act: -0.0000

Data Index: 1892176 (The Pile)

Max Activating Token Index: 519

Text #18

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.9765. Min Act: -0.0000

Data Index: 211747 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 3.9038. Min Range: -3.9038

Max Act: 2.6617. Min Act: -0.0000

Data Index: 556549 (The Pile)

Max Activating Token Index: 91