Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.4087. Min Act: -0.0000

Data Index: 948152 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1007867 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.4001. Min Act: -0.0000

Data Index: 60176 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3683. Min Act: -0.0000

Data Index: 270059 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1108634 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3653. Min Act: -0.0000

Data Index: 772765 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1291670 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3558. Min Act: -0.0001

Data Index: 220851 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3520. Min Act: -0.0000

Data Index: 842400 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3368. Min Act: -0.0000

Data Index: 667012 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3367. Min Act: -0.0000

Data Index: 1346721 (C4 (Web Text))

Max Activating Token Index: 509

Text #11

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3458. Min Act: -0.0000

Data Index: 844346 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3444. Min Act: -0.0000

Data Index: 232766 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3422. Min Act: -0.0000

Data Index: 926064 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3398. Min Act: -0.0000

Data Index: 505372 (C4 (Web Text))

Max Activating Token Index: 209

Text #15

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3398. Min Act: -0.0001

Data Index: 858054 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3266. Min Act: -0.0000

Data Index: 1249777 (C4 (Web Text))

Max Activating Token Index: 85

Text #17

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3384. Min Act: -0.0000

Data Index: 368846 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3364. Min Act: -0.0000

Data Index: 889460 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 0.4087. Min Range: -0.4087

Max Act: 0.3198. Min Act: -0.0000

Data Index: 254360 (C4 (Web Text))

Max Activating Token Index: 347