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

Dataset: The Pile

Neuron 4737 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: 1.7798. Min Range: -1.7798

Max Act: 1.7798. Min Act: -0.0000

Data Index: 1879619 (The Pile)

Max Activating Token Index: 259

Text #1

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.4029. Min Act: -0.0000

Data Index: 619472 (The Pile)

Max Activating Token Index: 345

Text #2

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.5468. Min Act: -0.0000

Data Index: 854123 (The Pile)

Max Activating Token Index: 786

Text #3

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3035. Min Act: -0.0000

Data Index: 1159694 (The Pile)

Max Activating Token Index: 886

Text #4

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.3163. Min Act: 0.0000

Data Index: 619088 (The Pile)

Max Activating Token Index: 468

Text #5

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.2649. Min Act: -0.0000

Data Index: 235437 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1605628 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.1786. Min Act: -0.0000

Data Index: 933762 (The Pile)

Max Activating Token Index: 1016

Text #8

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1271549 (The Pile)

Max Activating Token Index: 112

Text #9

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1821672 (The Pile)

Max Activating Token Index: 670

Text #10

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.1237. Min Act: -0.0000

Data Index: 320252 (The Pile)

Max Activating Token Index: 255

Text #11

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1147592 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.0402. Min Act: -0.0000

Data Index: 461090 (The Pile)

Max Activating Token Index: 114

Text #13

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.0767. Min Act: -0.0000

Data Index: 602882 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.1083. Min Act: -0.0000

Data Index: 46195 (The Pile)

Max Activating Token Index: 59

Text #15

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.0623. Min Act: -0.0000

Data Index: 540659 (The Pile)

Max Activating Token Index: 242

Text #16

Max Range: 1.7798. Min Range: -1.7798

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1603797 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 1.7798. Min Range: -1.7798

Max Act: 1.0455. Min Act: -0.0000

Data Index: 564686 (The Pile)

Max Activating Token Index: 964

Text #18

Max Range: 1.7798. Min Range: -1.7798

Max Act: 0.9788. Min Act: -0.0000

Data Index: 502342 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 1.7798. Min Range: -1.7798

Max Act: 0.9406. Min Act: -0.0000

Data Index: 538903 (The Pile)

Max Activating Token Index: 417