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

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

Neuron 3737 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.7744. Min Act: -0.0003

Data Index: 1407623 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.7761. Min Act: -0.0002

Data Index: 320117 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.7019. Min Act: -0.0002

Data Index: 944124 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.6423. Min Act: -0.0002

Data Index: 508732 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.6181. Min Act: -0.0002

Data Index: 1315991 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.6170. Min Act: -0.0002

Data Index: 1079652 (C4 (Web Text))

Max Activating Token Index: 734

Text #6

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.6061. Min Act: -0.0002

Data Index: 1496097 (Python Code)

Max Activating Token Index: 177

Text #7

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.6074. Min Act: -0.0003

Data Index: 37019 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5675. Min Act: -0.0003

Data Index: 971060 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5777. Min Act: -0.0003

Data Index: 515127 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5567. Min Act: -0.0002

Data Index: 1287561 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5491. Min Act: -0.0002

Data Index: 1330863 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5476. Min Act: -0.0002

Data Index: 937548 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5469. Min Act: -0.0003

Data Index: 1137856 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5422. Min Act: -0.0003

Data Index: 818586 (C4 (Web Text))

Max Activating Token Index: 379

Text #15

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5382. Min Act: -0.0003

Data Index: 615098 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5392. Min Act: -0.0003

Data Index: 1014992 (C4 (Web Text))

Max Activating Token Index: 370

Text #17

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5329. Min Act: -0.0003

Data Index: 781370 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5483. Min Act: -0.0002

Data Index: 196145 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.7761. Min Range: -0.7761

Max Act: 0.5226. Min Act: -0.0003

Data Index: 1193531 (C4 (Web Text))

Max Activating Token Index: 739