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

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

Neuron 4702 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.8078. Min Act: -0.0000

Data Index: 1271351 (C4 (Web Text))

Max Activating Token Index: 737

Text #1

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5949. Min Act: -0.0000

Data Index: 525330 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5118. Min Act: -0.0000

Data Index: 702828 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.5014. Min Act: -0.0000

Data Index: 316351 (C4 (Web Text))

Max Activating Token Index: 697

Text #4

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4562. Min Act: -0.0000

Data Index: 352323 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4467. Min Act: -0.0000

Data Index: 487995 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4374. Min Act: -0.0000

Data Index: 875317 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.4163. Min Act: -0.0000

Data Index: 1117547 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3783. Min Act: -0.0000

Data Index: 555268 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3430. Min Act: -0.0000

Data Index: 453095 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3698. Min Act: 0.0000

Data Index: 1578592 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3411. Min Act: -0.0000

Data Index: 173485 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1500516 (Python Code)

Max Activating Token Index: 606

Text #13

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3722. Min Act: -0.0000

Data Index: 1478720 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1016172 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3508. Min Act: -0.0000

Data Index: 457078 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3343. Min Act: -0.0000

Data Index: 1156774 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3261. Min Act: -0.0000

Data Index: 1599584 (Python Code)

Max Activating Token Index: 238

Text #18

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3359. Min Act: -0.0000

Data Index: 1524130 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 0.8078. Min Range: -0.8078

Max Act: 0.3410. Min Act: -0.0000

Data Index: 953757 (C4 (Web Text))

Max Activating Token Index: 155