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

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

Neuron 4220 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4414. Min Act: -0.0000

Data Index: 104142 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.6425. Min Act: -0.0000

Data Index: 504361 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.7023. Min Act: -0.0000

Data Index: 835025 (C4 (Web Text))

Max Activating Token Index: 414

Text #3

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.5751. Min Act: -0.0000

Data Index: 845865 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4617. Min Act: -0.0000

Data Index: 700431 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.3581. Min Act: -0.0000

Data Index: 719244 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.5957. Min Act: -0.0000

Data Index: 627106 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4776. Min Act: -0.0000

Data Index: 830162 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4263. Min Act: -0.0000

Data Index: 1150952 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4228. Min Act: -0.0000

Data Index: 311337 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.2941. Min Act: -0.0000

Data Index: 862272 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.3995. Min Act: -0.0000

Data Index: 715655 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4080. Min Act: -0.0000

Data Index: 663327 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4679. Min Act: -0.0000

Data Index: 366056 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4471. Min Act: -0.0000

Data Index: 498866 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.3033. Min Act: -0.0000

Data Index: 670164 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4338. Min Act: -0.0000

Data Index: 946588 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.4196. Min Act: -0.0000

Data Index: 145499 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.3797. Min Act: -0.0000

Data Index: 1201105 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 2.7023. Min Range: -2.7023

Max Act: 2.2479. Min Act: -0.0000

Data Index: 45606 (C4 (Web Text))

Max Activating Token Index: 858