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

Dataset: The Pile

Neuron 1785 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.7153. Min Act: -0.0000

Data Index: 875260 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6809. Min Act: -0.0000

Data Index: 309881 (The Pile)

Max Activating Token Index: 37

Text #2

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.7554. Min Act: 0.0000

Data Index: 1785921 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6697. Min Act: -0.0000

Data Index: 1198847 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6633. Min Act: -0.0000

Data Index: 183219 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6773. Min Act: -0.0000

Data Index: 770369 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1966617 (The Pile)

Max Activating Token Index: 43

Text #7

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6219. Min Act: 0.0000

Data Index: 589072 (The Pile)

Max Activating Token Index: 412

Text #8

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6661. Min Act: -0.0000

Data Index: 927748 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1980407 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1432851 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5525. Min Act: -0.0000

Data Index: 666128 (The Pile)

Max Activating Token Index: 1012

Text #12

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5948. Min Act: -0.0000

Data Index: 278036 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5491. Min Act: -0.0000

Data Index: 46506 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5249. Min Act: -0.0000

Data Index: 229631 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1015252 (The Pile)

Max Activating Token Index: 292

Text #16

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5434. Min Act: -0.0000

Data Index: 235460 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5381. Min Act: -0.0000

Data Index: 320297 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1348886 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.7554. Min Range: -0.7554

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1834979 (The Pile)

Max Activating Token Index: 50