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

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

Neuron 4608 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: 1.1266. Min Range: -1.1266

Max Act: 1.1266. Min Act: -0.0000

Data Index: 941839 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1166516 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1216652 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8749. Min Act: -0.0000

Data Index: 219230 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1338223 (C4 (Web Text))

Max Activating Token Index: 618

Text #5

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7893. Min Act: -0.0000

Data Index: 312141 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8420. Min Act: -0.0000

Data Index: 624398 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1243105 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8441. Min Act: -0.0000

Data Index: 958335 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.8200. Min Act: -0.0000

Data Index: 819223 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7485. Min Act: -0.0000

Data Index: 578778 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6980. Min Act: -0.0000

Data Index: 629084 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7297. Min Act: -0.0000

Data Index: 524113 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.7193. Min Act: -0.0000

Data Index: 191901 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6526. Min Act: -0.0000

Data Index: 665863 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6889. Min Act: -0.0000

Data Index: 288266 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6867. Min Act: -0.0000

Data Index: 906243 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6415. Min Act: -0.0000

Data Index: 369747 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6316. Min Act: -0.0000

Data Index: 1217749 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.1266. Min Range: -1.1266

Max Act: 0.6810. Min Act: -0.0000

Data Index: 873009 (C4 (Web Text))

Max Activating Token Index: 629