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

Dataset: The Pile

Neuron 1647 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: 1.0026. Min Range: -1.0026

Max Act: 1.0026. Min Act: -0.0000

Data Index: 182917 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1663270 (The Pile)

Max Activating Token Index: 70

Text #2

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8784. Min Act: -0.0000

Data Index: 743208 (The Pile)

Max Activating Token Index: 141

Text #3

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1671785 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8634. Min Act: -0.0000

Data Index: 829568 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.9173. Min Act: -0.0000

Data Index: 83414 (The Pile)

Max Activating Token Index: 484

Text #6

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8818. Min Act: -0.0000

Data Index: 1919961 (The Pile)

Max Activating Token Index: 1017

Text #7

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8673. Min Act: -0.0000

Data Index: 160592 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1662896 (The Pile)

Max Activating Token Index: 351

Text #9

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8606. Min Act: -0.0000

Data Index: 578150 (The Pile)

Max Activating Token Index: 32

Text #10

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8085. Min Act: -0.0000

Data Index: 1825895 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8475. Min Act: -0.0000

Data Index: 1345906 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1021558 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1824848 (The Pile)

Max Activating Token Index: 272

Text #14

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1081651 (The Pile)

Max Activating Token Index: 592

Text #15

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1425988 (The Pile)

Max Activating Token Index: 726

Text #16

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8892. Min Act: -0.0000

Data Index: 806009 (The Pile)

Max Activating Token Index: 503

Text #17

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8407. Min Act: -0.0000

Data Index: 870321 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8254. Min Act: -0.0000

Data Index: 30302 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 1.0026. Min Range: -1.0026

Max Act: 0.8615. Min Act: -0.0000

Data Index: 849604 (The Pile)

Max Activating Token Index: 162