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

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

Neuron 4799 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6696. Min Act: -0.0003

Data Index: 494780 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6590. Min Act: -0.0002

Data Index: 859135 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6788. Min Act: -0.0002

Data Index: 1204982 (C4 (Web Text))

Max Activating Token Index: 515

Text #3

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6545. Min Act: -0.0003

Data Index: 532471 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6566. Min Act: -0.0003

Data Index: 792903 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6300. Min Act: -0.0002

Data Index: 472213 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6288. Min Act: -0.0002

Data Index: 785762 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5691. Min Act: -0.0003

Data Index: 750317 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6034. Min Act: -0.0002

Data Index: 403701 (C4 (Web Text))

Max Activating Token Index: 293

Text #9

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5969. Min Act: -0.0003

Data Index: 922340 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.6137. Min Act: -0.0003

Data Index: 18448 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5737. Min Act: -0.0002

Data Index: 720724 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5692. Min Act: -0.0002

Data Index: 530579 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5831. Min Act: -0.0003

Data Index: 315286 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5812. Min Act: -0.0003

Data Index: 277744 (C4 (Web Text))

Max Activating Token Index: 959

Text #15

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5919. Min Act: -0.0003

Data Index: 242055 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5533. Min Act: -0.0003

Data Index: 125735 (C4 (Web Text))

Max Activating Token Index: 477

Text #17

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5640. Min Act: -0.0002

Data Index: 757263 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5580. Min Act: -0.0003

Data Index: 904849 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.6788. Min Range: -0.6788

Max Act: 0.5553. Min Act: -0.0002

Data Index: 54575 (C4 (Web Text))

Max Activating Token Index: 285