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

Dataset: The Pile

Neuron 890 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: 1.0409. Min Range: -1.0409

Max Act: 0.9158. Min Act: -0.0000

Data Index: 1089417 (The Pile)

Max Activating Token Index: 1005

Text #1

Max Range: 1.0409. Min Range: -1.0409

Max Act: 1.0409. Min Act: -0.0000

Data Index: 764386 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1873979 (The Pile)

Max Activating Token Index: 24

Text #3

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1946274 (The Pile)

Max Activating Token Index: 471

Text #4

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1488650 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1346542 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1307820 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.8547. Min Act: -0.0000

Data Index: 988448 (The Pile)

Max Activating Token Index: 544

Text #8

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7677. Min Act: -0.0000

Data Index: 794873 (The Pile)

Max Activating Token Index: 716

Text #9

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1874313 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7691. Min Act: -0.0000

Data Index: 724687 (The Pile)

Max Activating Token Index: 52

Text #11

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7567. Min Act: -0.0000

Data Index: 57003 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6981. Min Act: -0.0000

Data Index: 103375 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7495. Min Act: -0.0000

Data Index: 926395 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6511. Min Act: -0.0000

Data Index: 1056109 (The Pile)

Max Activating Token Index: 584

Text #15

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6840. Min Act: -0.0000

Data Index: 338172 (The Pile)

Max Activating Token Index: 956

Text #16

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6324. Min Act: -0.0000

Data Index: 601705 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1077410 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.7719. Min Act: -0.0000

Data Index: 1595319 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.0409. Min Range: -1.0409

Max Act: 0.6793. Min Act: -0.0000

Data Index: 352076 (The Pile)

Max Activating Token Index: 636