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

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

Neuron 2208 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: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0000

Data Index: 978541 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6918. Min Act: -0.0001

Data Index: 857756 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6380. Min Act: -0.0001

Data Index: 459677 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6234. Min Act: -0.0001

Data Index: 477009 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5987. Min Act: -0.0001

Data Index: 50611 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5788. Min Act: -0.0001

Data Index: 794620 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5594. Min Act: -0.0001

Data Index: 1057538 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5343. Min Act: -0.0001

Data Index: 1225970 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5438. Min Act: -0.0000

Data Index: 282948 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.4796. Min Act: -0.0001

Data Index: 899453 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5412. Min Act: -0.0001

Data Index: 106250 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5032. Min Act: -0.0000

Data Index: 216251 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5212. Min Act: -0.0001

Data Index: 1196712 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5162. Min Act: -0.0001

Data Index: 473291 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5075. Min Act: -0.0001

Data Index: 815522 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1272071 (C4 (Web Text))

Max Activating Token Index: 284

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.4985. Min Act: -0.0001

Data Index: 394618 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.4692. Min Act: -0.0001

Data Index: 892348 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.4965. Min Act: -0.0001

Data Index: 887782 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.4763. Min Act: -0.0001

Data Index: 884035 (C4 (Web Text))

Max Activating Token Index: 597