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

Dataset: The Pile

Neuron 3981 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: 1.8474. Min Range: -1.8474

Max Act: 1.8405. Min Act: -0.0000

Data Index: 316880 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.8474. Min Act: -0.0000

Data Index: 1636011 (The Pile)

Max Activating Token Index: 139

Text #2

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.7426. Min Act: -0.0000

Data Index: 989477 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.7767. Min Act: -0.0000

Data Index: 1807763 (The Pile)

Max Activating Token Index: 96

Text #4

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.8013. Min Act: -0.0000

Data Index: 773769 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6982. Min Act: -0.0000

Data Index: 1917831 (The Pile)

Max Activating Token Index: 576

Text #6

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5450. Min Act: -0.0000

Data Index: 1437572 (The Pile)

Max Activating Token Index: 189

Text #7

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5691. Min Act: -0.0000

Data Index: 1982389 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1663027 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4880. Min Act: -0.0000

Data Index: 926542 (The Pile)

Max Activating Token Index: 511

Text #10

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6127. Min Act: -0.0000

Data Index: 286477 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5492. Min Act: -0.0000

Data Index: 1198672 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6295. Min Act: -0.0000

Data Index: 722147 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5469. Min Act: -0.0000

Data Index: 1664984 (The Pile)

Max Activating Token Index: 716

Text #14

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1739623 (The Pile)

Max Activating Token Index: 981

Text #15

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4317. Min Act: -0.0000

Data Index: 1082502 (The Pile)

Max Activating Token Index: 211

Text #16

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.6096. Min Act: -0.0000

Data Index: 545650 (The Pile)

Max Activating Token Index: 836

Text #17

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1097289 (The Pile)

Max Activating Token Index: 925

Text #18

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.5846. Min Act: -0.0000

Data Index: 563572 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 1.8474. Min Range: -1.8474

Max Act: 1.4582. Min Act: -0.0000

Data Index: 1553029 (The Pile)

Max Activating Token Index: 23