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

Dataset: The Pile

Neuron 2576 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: 1.0068. Min Range: -1.0068

Max Act: 1.0068. Min Act: -0.0000

Data Index: 843415 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7921. Min Act: -0.0000

Data Index: 530197 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1136581 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1253961 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6935. Min Act: -0.0000

Data Index: 702965 (The Pile)

Max Activating Token Index: 183

Text #5

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6300. Min Act: -0.0000

Data Index: 232793 (The Pile)

Max Activating Token Index: 865

Text #6

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6346. Min Act: -0.0000

Data Index: 285135 (The Pile)

Max Activating Token Index: 710

Text #7

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1526013 (The Pile)

Max Activating Token Index: 394

Text #8

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6073. Min Act: -0.0000

Data Index: 711520 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6037. Min Act: 0.0000

Data Index: 1641624 (The Pile)

Max Activating Token Index: 526

Text #10

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6138. Min Act: -0.0000

Data Index: 824806 (The Pile)

Max Activating Token Index: 896

Text #11

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1256852 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.6184. Min Act: -0.0000

Data Index: 754727 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1600633 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5577. Min Act: -0.0000

Data Index: 1291951 (The Pile)

Max Activating Token Index: 172

Text #15

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5550. Min Act: 0.0000

Data Index: 1762404 (The Pile)

Max Activating Token Index: 985

Text #16

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5544. Min Act: -0.0000

Data Index: 562744 (The Pile)

Max Activating Token Index: 482

Text #17

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5289. Min Act: -0.0000

Data Index: 918367 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5268. Min Act: 0.0000

Data Index: 1264775 (The Pile)

Max Activating Token Index: 227

Text #19

Max Range: 1.0068. Min Range: -1.0068

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1468977 (The Pile)

Max Activating Token Index: 908