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

Dataset: The Pile

Neuron 271 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: 1.4492. Min Range: -1.4492

Max Act: 1.4492. Min Act: -0.0000

Data Index: 308893 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.1222. Min Act: -0.0000

Data Index: 489234 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.1276. Min Act: -0.0000

Data Index: 1027830 (The Pile)

Max Activating Token Index: 859

Text #3

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.0417. Min Act: -0.0000

Data Index: 25373 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 1.4492. Min Range: -1.4492

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1078303 (The Pile)

Max Activating Token Index: 899

Text #5

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9596. Min Act: -0.0000

Data Index: 896103 (The Pile)

Max Activating Token Index: 461

Text #6

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1975179 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9094. Min Act: -0.0000

Data Index: 83237 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1297502 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.8778. Min Act: -0.0000

Data Index: 926660 (The Pile)

Max Activating Token Index: 293

Text #10

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.8727. Min Act: -0.0000

Data Index: 242276 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1501592 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9189. Min Act: -0.0000

Data Index: 133388 (The Pile)

Max Activating Token Index: 251

Text #13

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9202. Min Act: -0.0000

Data Index: 1550434 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9305. Min Act: -0.0000

Data Index: 428119 (The Pile)

Max Activating Token Index: 357

Text #15

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.8052. Min Act: -0.0000

Data Index: 460295 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.9075. Min Act: -0.0000

Data Index: 1085227 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1093290 (The Pile)

Max Activating Token Index: 882

Text #18

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.8503. Min Act: -0.0000

Data Index: 1845722 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 1.4492. Min Range: -1.4492

Max Act: 0.8846. Min Act: -0.0000

Data Index: 921029 (The Pile)

Max Activating Token Index: 537