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

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

Neuron 61 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.4017. Min Act: -0.0000

Data Index: 343932 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.3498. Min Act: -0.0000

Data Index: 396093 (C4 (Web Text))

Max Activating Token Index: 914

Text #2

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.3847. Min Act: -0.0000

Data Index: 426682 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.2723. Min Act: -0.0000

Data Index: 948646 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0140. Min Act: -0.0000

Data Index: 134924 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0588. Min Act: 0.0000

Data Index: 348998 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.1270. Min Act: 0.0000

Data Index: 369244 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.9393. Min Act: -0.0000

Data Index: 25305 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.9814. Min Act: -0.0000

Data Index: 371143 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.9613. Min Act: -0.0000

Data Index: 1352696 (C4 (Web Text))

Max Activating Token Index: 523

Text #10

Max Range: 1.4017. Min Range: -1.4017

Max Act: 1.0590. Min Act: -0.0000

Data Index: 657637 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.9316. Min Act: -0.0000

Data Index: 10268 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8426. Min Act: -0.0000

Data Index: 1116589 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1183633 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8582. Min Act: 0.0000

Data Index: 854317 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8607. Min Act: -0.0000

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.7849. Min Act: -0.0000

Data Index: 674585 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8682. Min Act: 0.0000

Data Index: 1305140 (C4 (Web Text))

Max Activating Token Index: 419

Text #18

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8602. Min Act: -0.0000

Data Index: 1045726 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.4017. Min Range: -1.4017

Max Act: 0.8115. Min Act: -0.0000

Data Index: 798530 (C4 (Web Text))

Max Activating Token Index: 624