Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5361 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8206. Min Act: -0.0000

Data Index: 746099 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.8467. Min Act: 0.0000

Data Index: 813396 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6542. Min Act: -0.0000

Data Index: 52220 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6180. Min Act: -0.0000

Data Index: 113882 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5791. Min Act: -0.0000

Data Index: 52754 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5951. Min Act: -0.0000

Data Index: 532536 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5959. Min Act: -0.0000

Data Index: 174592 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1003502 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1216446 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1614005 (Python Code)

Max Activating Token Index: 1012

Text #10

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5933. Min Act: 0.0000

Data Index: 1100854 (C4 (Web Text))

Max Activating Token Index: 362

Text #11

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5537. Min Act: -0.0000

Data Index: 104370 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5351. Min Act: 0.0000

Data Index: 498858 (C4 (Web Text))

Max Activating Token Index: 262

Text #13

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5339. Min Act: -0.0000

Data Index: 1099835 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5422. Min Act: -0.0000

Data Index: 650297 (C4 (Web Text))

Max Activating Token Index: 624

Text #15

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5418. Min Act: -0.0000

Data Index: 394395 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5252. Min Act: -0.0000

Data Index: 471571 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5578. Min Act: -0.0000

Data Index: 381381 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.4884. Min Act: -0.0000

Data Index: 697132 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.8467. Min Range: -0.8467

Max Act: 0.5145. Min Act: -0.0000

Data Index: 1239054 (C4 (Web Text))

Max Activating Token Index: 70