Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1846 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5313. Min Act: -0.0001

Data Index: 172212 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4791. Min Act: -0.0001

Data Index: 1262360 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.5091. Min Act: -0.0001

Data Index: 530985 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4880. Min Act: -0.0001

Data Index: 589181 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4662. Min Act: -0.0001

Data Index: 452606 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4493. Min Act: -0.0001

Data Index: 1136895 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4545. Min Act: -0.0002

Data Index: 452837 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4688. Min Act: -0.0001

Data Index: 39592 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4667. Min Act: -0.0002

Data Index: 313069 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4251. Min Act: -0.0001

Data Index: 479353 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4245. Min Act: -0.0002

Data Index: 115118 (C4 (Web Text))

Max Activating Token Index: 581

Text #11

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4472. Min Act: -0.0001

Data Index: 899088 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4209. Min Act: -0.0001

Data Index: 844098 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.3988. Min Act: -0.0001

Data Index: 305582 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4452. Min Act: -0.0001

Data Index: 270925 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4535. Min Act: -0.0001

Data Index: 69892 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4363. Min Act: -0.0001

Data Index: 724782 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4506. Min Act: -0.0001

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4221. Min Act: -0.0001

Data Index: 111255 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.5313. Min Range: -0.5313

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1262446 (C4 (Web Text))

Max Activating Token Index: 30