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

Dataset: The Pile

Neuron 3121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.4628. Min Act: -0.0000

Data Index: 1066187 (The Pile)

Max Activating Token Index: 633

Text #1

Max Range: 3.4628. Min Range: -3.4628

Max Act: 3.1872. Min Act: -0.0000

Data Index: 1844276 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.8228. Min Act: -0.0000

Data Index: 602164 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.6564. Min Act: -0.0000

Data Index: 821918 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.7508. Min Act: -0.0000

Data Index: 1458239 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.6145. Min Act: -0.0000

Data Index: 749775 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.4397. Min Act: -0.0000

Data Index: 1119751 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.2992. Min Act: -0.0000

Data Index: 1811544 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.5392. Min Act: -0.0000

Data Index: 1453700 (The Pile)

Max Activating Token Index: 527

Text #9

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.3839. Min Act: -0.0000

Data Index: 1118308 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.3465. Min Act: -0.0000

Data Index: 364493 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.3778. Min Act: -0.0000

Data Index: 784462 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.4878. Min Act: -0.0000

Data Index: 41536 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.2255. Min Act: -0.0000

Data Index: 1512240 (The Pile)

Max Activating Token Index: 879

Text #14

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.4706. Min Act: -0.0000

Data Index: 518756 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.5631. Min Act: -0.0000

Data Index: 1678702 (The Pile)

Max Activating Token Index: 154

Text #16

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.4542. Min Act: -0.0000

Data Index: 1917217 (The Pile)

Max Activating Token Index: 534

Text #17

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.5939. Min Act: -0.0000

Data Index: 1421073 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.2887. Min Act: -0.0000

Data Index: 1063223 (The Pile)

Max Activating Token Index: 940

Text #19

Max Range: 3.4628. Min Range: -3.4628

Max Act: 2.3934. Min Act: -0.0000

Data Index: 1252262 (The Pile)

Max Activating Token Index: 335