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

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

Neuron 2007 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6468. Min Act: -0.0000

Data Index: 762282 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6069. Min Act: -0.0000

Data Index: 357509 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.6047. Min Act: -0.0000

Data Index: 1048467 (C4 (Web Text))

Max Activating Token Index: 153

Text #3

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5425. Min Act: -0.0000

Data Index: 759324 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5320. Min Act: -0.0000

Data Index: 373127 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5820. Min Act: -0.0000

Data Index: 940241 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5484. Min Act: -0.0000

Data Index: 973578 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1105279 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5397. Min Act: -0.0000

Data Index: 97318 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1237443 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4810. Min Act: -0.0000

Data Index: 316559 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1276999 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4966. Min Act: -0.0000

Data Index: 46601 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4951. Min Act: -0.0000

Data Index: 886624 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1161266 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4850. Min Act: -0.0000

Data Index: 332741 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4791. Min Act: -0.0000

Data Index: 26266 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.5082. Min Act: -0.0000

Data Index: 1312084 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4657. Min Act: -0.0000

Data Index: 343357 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 0.6468. Min Range: -0.6468

Max Act: 0.4781. Min Act: -0.0000

Data Index: 543671 (C4 (Web Text))

Max Activating Token Index: 107