Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1609 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0486. Min Act: -0.0002

Data Index: 1176268 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0487. Min Act: -0.0002

Data Index: 1313282 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0002

Data Index: 840261 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0474. Min Act: -0.0002

Data Index: 349210 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0469. Min Act: -0.0002

Data Index: 557354 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0453. Min Act: -0.0001

Data Index: 371836 (C4 (Web Text))

Max Activating Token Index: 90

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0444. Min Act: -0.0002

Data Index: 124567 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0458. Min Act: -0.0002

Data Index: 595377 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0428. Min Act: -0.0001

Data Index: 915987 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1044113 (C4 (Web Text))

Max Activating Token Index: 781

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0433. Min Act: -0.0002

Data Index: 756410 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0427. Min Act: -0.0002

Data Index: 572751 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0412. Min Act: -0.0002

Data Index: 351495 (C4 (Web Text))

Max Activating Token Index: 632

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1042225 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0427. Min Act: -0.0002

Data Index: 1040169 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0431. Min Act: -0.0002

Data Index: 1184256 (C4 (Web Text))

Max Activating Token Index: 580

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0424. Min Act: -0.0001

Data Index: 61547 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0415. Min Act: -0.0002

Data Index: 952445 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0421. Min Act: -0.0002

Data Index: 1261764 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0418. Min Act: -0.0002

Data Index: 928290 (C4 (Web Text))

Max Activating Token Index: 878