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

Dataset: The Pile

Neuron 1329 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1101. Min Act: -0.0000

Data Index: 348480 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1505294 (The Pile)

Max Activating Token Index: 72

Text #2

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1976062 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.1266. Min Act: -0.0000

Data Index: 274940 (The Pile)

Max Activating Token Index: 87

Text #4

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0390. Min Act: -0.0000

Data Index: 740357 (The Pile)

Max Activating Token Index: 742

Text #5

Max Range: 1.1633. Min Range: -1.1633

Max Act: 1.0260. Min Act: -0.0000

Data Index: 769384 (The Pile)

Max Activating Token Index: 323

Text #6

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1884356 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1940961 (The Pile)

Max Activating Token Index: 89

Text #8

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9482. Min Act: -0.0000

Data Index: 593449 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9312. Min Act: -0.0000

Data Index: 1820302 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8835. Min Act: -0.0000

Data Index: 621742 (The Pile)

Max Activating Token Index: 704

Text #11

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9185. Min Act: -0.0000

Data Index: 866267 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.9928. Min Act: -0.0000

Data Index: 188726 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7681. Min Act: -0.0000

Data Index: 289053 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7872. Min Act: -0.0000

Data Index: 917470 (The Pile)

Max Activating Token Index: 652

Text #15

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1739224 (The Pile)

Max Activating Token Index: 321

Text #16

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8039. Min Act: -0.0000

Data Index: 1505103 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.8205. Min Act: -0.0000

Data Index: 1182323 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1551004 (The Pile)

Max Activating Token Index: 733

Text #19

Max Range: 1.1633. Min Range: -1.1633

Max Act: 0.7188. Min Act: -0.0000

Data Index: 511836 (The Pile)

Max Activating Token Index: 121