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

Dataset: The Pile

Neuron 1168 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.3221. Min Act: -0.0000

Data Index: 681938 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1928. Min Act: -0.0000

Data Index: 153934 (The Pile)

Max Activating Token Index: 560

Text #2

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1819. Min Act: -0.0000

Data Index: 1231797 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1093077 (The Pile)

Max Activating Token Index: 784

Text #4

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1673088 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0962. Min Act: -0.0000

Data Index: 896331 (The Pile)

Max Activating Token Index: 781

Text #6

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0734. Min Act: -0.0000

Data Index: 1764607 (The Pile)

Max Activating Token Index: 752

Text #7

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0353. Min Act: -0.0000

Data Index: 624297 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.1004. Min Act: -0.0000

Data Index: 1636111 (The Pile)

Max Activating Token Index: 15

Text #9

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9989. Min Act: -0.0000

Data Index: 952610 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0008. Min Act: -0.0000

Data Index: 1850292 (The Pile)

Max Activating Token Index: 407

Text #11

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1171948 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9852. Min Act: -0.0000

Data Index: 178684 (The Pile)

Max Activating Token Index: 290

Text #13

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1495819 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0051. Min Act: 0.0001

Data Index: 303320 (The Pile)

Max Activating Token Index: 111

Text #15

Max Range: 1.3221. Min Range: -1.3221

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1398701 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9619. Min Act: 0.0000

Data Index: 1068204 (The Pile)

Max Activating Token Index: 1010

Text #17

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9234. Min Act: -0.0000

Data Index: 664542 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9779. Min Act: -0.0000

Data Index: 112436 (The Pile)

Max Activating Token Index: 332

Text #19

Max Range: 1.3221. Min Range: -1.3221

Max Act: 0.9710. Min Act: -0.0000

Data Index: 75913 (The Pile)

Max Activating Token Index: 468