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

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

Neuron 3773 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.3805. Min Act: -0.0001

Data Index: 655484 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.2400. Min Act: -0.0001

Data Index: 1520937 (Python Code)

Max Activating Token Index: 633

Text #2

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.0991. Min Act: -0.0001

Data Index: 1553612 (Python Code)

Max Activating Token Index: 695

Text #3

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.1728. Min Act: -0.0001

Data Index: 654951 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.1534. Min Act: -0.0001

Data Index: 1056995 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.1344. Min Act: -0.0001

Data Index: 1622519 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.0831. Min Act: -0.0001

Data Index: 831616 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.0196. Min Act: -0.0001

Data Index: 1309661 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9794. Min Act: -0.0001

Data Index: 1254776 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9729. Min Act: -0.0001

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.0841. Min Act: -0.0001

Data Index: 152169 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9871. Min Act: -0.0001

Data Index: 283732 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 1.3805. Min Range: -1.3805

Max Act: 1.0026. Min Act: -0.0001

Data Index: 754464 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9372. Min Act: -0.0001

Data Index: 865041 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9591. Min Act: -0.0001

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9251. Min Act: -0.0001

Data Index: 526184 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9258. Min Act: -0.0001

Data Index: 1365165 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9026. Min Act: -0.0001

Data Index: 1329355 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9030. Min Act: -0.0001

Data Index: 341002 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 1.3805. Min Range: -1.3805

Max Act: 0.9291. Min Act: -0.0001

Data Index: 387400 (C4 (Web Text))

Max Activating Token Index: 861