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

Dataset: The Pile

Neuron 2524 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0428. Min Range: -1.0428

Max Act: 1.0428. Min Act: -0.0000

Data Index: 1661377 (The Pile)

Max Activating Token Index: 88

Text #1

Max Range: 1.0428. Min Range: -1.0428

Max Act: 1.0040. Min Act: -0.0000

Data Index: 734401 (The Pile)

Max Activating Token Index: 183

Text #2

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9229. Min Act: -0.0000

Data Index: 1423911 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1249014 (The Pile)

Max Activating Token Index: 90

Text #4

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1683013 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1019791 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1855041 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8428. Min Act: -0.0000

Data Index: 950358 (The Pile)

Max Activating Token Index: 232

Text #8

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1420566 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8313. Min Act: -0.0000

Data Index: 382830 (The Pile)

Max Activating Token Index: 267

Text #10

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7962. Min Act: -0.0000

Data Index: 1616309 (The Pile)

Max Activating Token Index: 303

Text #11

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7436. Min Act: -0.0000

Data Index: 54640 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7792. Min Act: -0.0000

Data Index: 1695841 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8066. Min Act: -0.0000

Data Index: 829499 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.8048. Min Act: -0.0000

Data Index: 226210 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7569. Min Act: -0.0000

Data Index: 184961 (The Pile)

Max Activating Token Index: 455

Text #16

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7613. Min Act: -0.0000

Data Index: 323574 (The Pile)

Max Activating Token Index: 518

Text #17

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7418. Min Act: -0.0000

Data Index: 871904 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1066815 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 1.0428. Min Range: -1.0428

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1423967 (The Pile)

Max Activating Token Index: 445