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

Dataset: The Pile

Neuron 700 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2276. Min Range: -1.2276

Max Act: 1.2276. Min Act: -0.0000

Data Index: 1775762 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1924894 (The Pile)

Max Activating Token Index: 703

Text #2

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1703943 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1788435 (The Pile)

Max Activating Token Index: 122

Text #4

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8330. Min Act: -0.0000

Data Index: 396512 (The Pile)

Max Activating Token Index: 761

Text #5

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.9572. Min Act: -0.0000

Data Index: 537786 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8925. Min Act: -0.0000

Data Index: 776998 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8887. Min Act: -0.0000

Data Index: 1128131 (The Pile)

Max Activating Token Index: 145

Text #8

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1127108 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1149222 (The Pile)

Max Activating Token Index: 529

Text #10

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1336420 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.7906. Min Act: -0.0000

Data Index: 396495 (The Pile)

Max Activating Token Index: 752

Text #12

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8606. Min Act: -0.0000

Data Index: 464084 (The Pile)

Max Activating Token Index: 135

Text #13

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8289. Min Act: -0.0000

Data Index: 1050716 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.8346. Min Act: -0.0000

Data Index: 665957 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.7353. Min Act: -0.0000

Data Index: 550490 (The Pile)

Max Activating Token Index: 111

Text #16

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.7650. Min Act: -0.0000

Data Index: 169521 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1979116 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.7023. Min Act: -0.0000

Data Index: 337228 (The Pile)

Max Activating Token Index: 262

Text #19

Max Range: 1.2276. Min Range: -1.2276

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1796783 (The Pile)

Max Activating Token Index: 508