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

Dataset: The Pile

Neuron 3122 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.8710. Min Act: -0.0000

Data Index: 1495413 (The Pile)

Max Activating Token Index: 608

Text #1

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7365. Min Act: -0.0000

Data Index: 346979 (The Pile)

Max Activating Token Index: 41

Text #2

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7852. Min Act: -0.0000

Data Index: 180872 (The Pile)

Max Activating Token Index: 430

Text #3

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5746. Min Act: -0.0000

Data Index: 1570588 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5295. Min Act: -0.0000

Data Index: 619872 (The Pile)

Max Activating Token Index: 166

Text #5

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.7391. Min Act: -0.0000

Data Index: 1028053 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5440. Min Act: -0.0000

Data Index: 407029 (The Pile)

Max Activating Token Index: 439

Text #7

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4246. Min Act: -0.0000

Data Index: 266417 (The Pile)

Max Activating Token Index: 217

Text #8

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1600573 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.5124. Min Act: -0.0000

Data Index: 1607689 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3210. Min Act: -0.0000

Data Index: 814541 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2713. Min Act: -0.0000

Data Index: 1792651 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3324. Min Act: -0.0000

Data Index: 1535344 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3089. Min Act: -0.0000

Data Index: 986470 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.1764. Min Act: -0.0000

Data Index: 324702 (The Pile)

Max Activating Token Index: 769

Text #15

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1670328 (The Pile)

Max Activating Token Index: 810

Text #16

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1628797 (The Pile)

Max Activating Token Index: 12

Text #17

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2454. Min Act: -0.0000

Data Index: 1564375 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.2390. Min Act: -0.0000

Data Index: 811152 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 1.8710. Min Range: -1.8710

Max Act: 1.3629. Min Act: -0.0000

Data Index: 1767250 (The Pile)

Max Activating Token Index: 959