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

Dataset: The Pile

Neuron 3162 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.8891. Min Act: -0.0000

Data Index: 375008 (The Pile)

Max Activating Token Index: 799

Text #1

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.7078. Min Act: -0.0000

Data Index: 1897140 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.7289. Min Act: -0.0000

Data Index: 1291389 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.6424. Min Act: -0.0000

Data Index: 1359480 (The Pile)

Max Activating Token Index: 520

Text #4

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.6296. Min Act: -0.0001

Data Index: 120752 (The Pile)

Max Activating Token Index: 644

Text #5

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.6831. Min Act: -0.0000

Data Index: 1097768 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.6900. Min Act: -0.0000

Data Index: 780587 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5610. Min Act: -0.0000

Data Index: 987068 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.6205. Min Act: -0.0000

Data Index: 641054 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.6965. Min Act: -0.0000

Data Index: 1883994 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1862453 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.3906. Min Act: -0.0000

Data Index: 838988 (The Pile)

Max Activating Token Index: 677

Text #12

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5408. Min Act: -0.0000

Data Index: 127413 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5425. Min Act: -0.0000

Data Index: 1700415 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.4430. Min Act: -0.0000

Data Index: 1363407 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5209. Min Act: -0.0000

Data Index: 1268333 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5116. Min Act: -0.0000

Data Index: 152115 (The Pile)

Max Activating Token Index: 74

Text #17

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5655. Min Act: -0.0000

Data Index: 162021 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.4442. Min Act: -0.0000

Data Index: 1051020 (The Pile)

Max Activating Token Index: 767

Text #19

Max Range: 1.8891. Min Range: -1.8891

Max Act: 1.5760. Min Act: -0.0000

Data Index: 935856 (The Pile)

Max Activating Token Index: 550