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

Dataset: The Pile

Neuron 1170 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: 1.0018. Min Range: -1.0018

Max Act: 1.0018. Min Act: -0.0000

Data Index: 893007 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1572797 (The Pile)

Max Activating Token Index: 808

Text #2

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1777147 (The Pile)

Max Activating Token Index: 757

Text #3

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.9217. Min Act: -0.0000

Data Index: 561332 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.9210. Min Act: -0.0000

Data Index: 244740 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8786. Min Act: -0.0000

Data Index: 912067 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8807. Min Act: -0.0000

Data Index: 48196 (The Pile)

Max Activating Token Index: 339

Text #7

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1861651 (The Pile)

Max Activating Token Index: 482

Text #8

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8417. Min Act: -0.0000

Data Index: 136813 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8591. Min Act: -0.0000

Data Index: 496536 (The Pile)

Max Activating Token Index: 669

Text #10

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8046. Min Act: -0.0000

Data Index: 620253 (The Pile)

Max Activating Token Index: 510

Text #11

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1232704 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8169. Min Act: -0.0000

Data Index: 130034 (The Pile)

Max Activating Token Index: 513

Text #13

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1834186 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7493. Min Act: -0.0000

Data Index: 482702 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7842. Min Act: -0.0000

Data Index: 970740 (The Pile)

Max Activating Token Index: 456

Text #16

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7274. Min Act: -0.0000

Data Index: 269266 (The Pile)

Max Activating Token Index: 438

Text #17

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7399. Min Act: -0.0000

Data Index: 1195773 (The Pile)

Max Activating Token Index: 531

Text #18

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1181639 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 1.0018. Min Range: -1.0018

Max Act: 0.7662. Min Act: -0.0000

Data Index: 1097883 (The Pile)

Max Activating Token Index: 263