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

Dataset: The Pile

Neuron 2125 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: 1.5843. Min Range: -1.5843

Max Act: 1.5843. Min Act: -0.0000

Data Index: 522984 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.5446. Min Act: 0.0000

Data Index: 1961895 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.3234. Min Act: -0.0000

Data Index: 717513 (The Pile)

Max Activating Token Index: 214

Text #3

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1402. Min Act: -0.0000

Data Index: 1107662 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1658. Min Act: -0.0000

Data Index: 754040 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1176252 (The Pile)

Max Activating Token Index: 218

Text #6

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1886857 (The Pile)

Max Activating Token Index: 149

Text #7

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9799. Min Act: -0.0000

Data Index: 366370 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 1.5843. Min Range: -1.5843

Max Act: 1.0900. Min Act: -0.0000

Data Index: 210912 (The Pile)

Max Activating Token Index: 466

Text #9

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1475208 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9704. Min Act: -0.0000

Data Index: 851837 (The Pile)

Max Activating Token Index: 280

Text #11

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9516. Min Act: 0.0000

Data Index: 1942532 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.7832. Min Act: -0.0000

Data Index: 1405966 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9387. Min Act: -0.0000

Data Index: 1247753 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.8932. Min Act: -0.0000

Data Index: 1244995 (The Pile)

Max Activating Token Index: 420

Text #15

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.7990. Min Act: -0.0000

Data Index: 877248 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9491. Min Act: -0.0000

Data Index: 673640 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1983825 (The Pile)

Max Activating Token Index: 500

Text #18

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.6938. Min Act: -0.0000

Data Index: 48852 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 1.5843. Min Range: -1.5843

Max Act: 0.8487. Min Act: 0.0000

Data Index: 177430 (The Pile)

Max Activating Token Index: 477