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

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

Neuron 3037 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0000

Data Index: 20091 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0520. Min Act: -0.0000

Data Index: 334660 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1179480 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0486. Min Act: -0.0001

Data Index: 21262 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0453. Min Act: -0.0000

Data Index: 476641 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0479. Min Act: -0.0000

Data Index: 466047 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0438. Min Act: -0.0000

Data Index: 1110000 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0399. Min Act: -0.0000

Data Index: 599237 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0454. Min Act: -0.0000

Data Index: 1324483 (C4 (Web Text))

Max Activating Token Index: 90

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0405. Min Act: -0.0000

Data Index: 1211554 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0405. Min Act: -0.0000

Data Index: 928185 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0421. Min Act: -0.0000

Data Index: 314933 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0441. Min Act: -0.0000

Data Index: 1044713 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0414. Min Act: -0.0000

Data Index: 29488 (C4 (Web Text))

Max Activating Token Index: 278

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0428. Min Act: -0.0000

Data Index: 995956 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0410. Min Act: -0.0000

Data Index: 1341586 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0411. Min Act: -0.0000

Data Index: 1640273 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0410. Min Act: -0.0000

Data Index: 57310 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0406. Min Act: -0.0000

Data Index: 578326 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0414. Min Act: -0.0000

Data Index: 981397 (C4 (Web Text))

Max Activating Token Index: 42