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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1956 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7468. Min Range: -5.7468

Max Act: 5.7468. Min Act: -0.0000

Data Index: 901687 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 5.7468. Min Range: -5.7468

Max Act: 5.3820. Min Act: -0.0001

Data Index: 498343 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.8051. Min Act: -0.0001

Data Index: 1149728 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 5.7468. Min Range: -5.7468

Max Act: 5.4513. Min Act: -0.0001

Data Index: 917519 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.4286. Min Act: -0.0001

Data Index: 348410 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.8373. Min Act: -0.0000

Data Index: 585367 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.5029. Min Act: -0.0000

Data Index: 585665 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.6223. Min Act: -0.0001

Data Index: 644150 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.6352. Min Act: -0.0001

Data Index: 985389 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.7766. Min Act: -0.0001

Data Index: 1263487 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.4374. Min Act: -0.0001

Data Index: 1141688 (C4 (Web Text))

Max Activating Token Index: 743

Text #11

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.4353. Min Act: -0.0001

Data Index: 296807 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.6056. Min Act: -0.0001

Data Index: 642640 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.6987. Min Act: -0.0001

Data Index: 155746 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.3545. Min Act: -0.0001

Data Index: 654188 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.3539. Min Act: -0.0001

Data Index: 17748 (C4 (Web Text))

Max Activating Token Index: 14

Text #16

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.4077. Min Act: -0.0000

Data Index: 582991 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.2284. Min Act: -0.0000

Data Index: 1176048 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.3721. Min Act: -0.0000

Data Index: 654365 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 5.7468. Min Range: -5.7468

Max Act: 4.2061. Min Act: -0.0000

Data Index: 552609 (C4 (Web Text))

Max Activating Token Index: 199