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

Dataset: The Pile

Neuron 4376 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: 1.0695. Min Range: -1.0695

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1762600 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1488825 (The Pile)

Max Activating Token Index: 165

Text #2

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1343256 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1935927 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7858. Min Act: -0.0000

Data Index: 1378846 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1997739 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7761. Min Act: -0.0000

Data Index: 177740 (The Pile)

Max Activating Token Index: 576

Text #7

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7841. Min Act: -0.0000

Data Index: 1278745 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.8265. Min Act: -0.0000

Data Index: 986018 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1630120 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7630. Min Act: 0.0000

Data Index: 1019322 (The Pile)

Max Activating Token Index: 662

Text #11

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7634. Min Act: -0.0000

Data Index: 685032 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1520593 (The Pile)

Max Activating Token Index: 84

Text #13

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7058. Min Act: -0.0000

Data Index: 1782412 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.6528. Min Act: -0.0000

Data Index: 1081352 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7267. Min Act: -0.0000

Data Index: 72026 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7239. Min Act: -0.0000

Data Index: 1047021 (The Pile)

Max Activating Token Index: 55

Text #17

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1989144 (The Pile)

Max Activating Token Index: 834

Text #18

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7168. Min Act: -0.0000

Data Index: 731181 (The Pile)

Max Activating Token Index: 632

Text #19

Max Range: 1.0695. Min Range: -1.0695

Max Act: 0.7225. Min Act: 0.0000

Data Index: 1380648 (The Pile)

Max Activating Token Index: 442