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

Dataset: The Pile

Neuron 3819 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.8486. Min Act: -0.0000

Data Index: 1589052 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.7179. Min Act: -0.0000

Data Index: 932775 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.7221. Min Act: -0.0000

Data Index: 876233 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6429. Min Act: -0.0000

Data Index: 814595 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5424. Min Act: -0.0000

Data Index: 239212 (The Pile)

Max Activating Token Index: 802

Text #5

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1223107 (The Pile)

Max Activating Token Index: 149

Text #6

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1820866 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6748. Min Act: -0.0000

Data Index: 1439492 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1329087 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5941. Min Act: -0.0000

Data Index: 440800 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1168029 (The Pile)

Max Activating Token Index: 235

Text #11

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6091. Min Act: -0.0000

Data Index: 1681712 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6055. Min Act: -0.0000

Data Index: 674994 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1184333 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1142898 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1102021 (The Pile)

Max Activating Token Index: 173

Text #16

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.4439. Min Act: -0.0000

Data Index: 1604248 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5933. Min Act: -0.0000

Data Index: 998469 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5606. Min Act: -0.0000

Data Index: 708078 (The Pile)

Max Activating Token Index: 921

Text #19

Max Range: 0.8486. Min Range: -0.8486

Max Act: 0.5732. Min Act: -0.0000

Data Index: 160951 (The Pile)

Max Activating Token Index: 147