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

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

Neuron 3501 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7509. Min Act: -0.0001

Data Index: 1174856 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6980. Min Act: -0.0001

Data Index: 1134889 (C4 (Web Text))

Max Activating Token Index: 355

Text #2

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6173. Min Act: -0.0001

Data Index: 684454 (C4 (Web Text))

Max Activating Token Index: 529

Text #3

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.7161. Min Act: -0.0001

Data Index: 1143972 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6281. Min Act: -0.0001

Data Index: 506158 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5731. Min Act: -0.0001

Data Index: 1338536 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6203. Min Act: -0.0001

Data Index: 282725 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1332636 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5350. Min Act: -0.0001

Data Index: 319500 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5834. Min Act: -0.0001

Data Index: 564339 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5953. Min Act: -0.0001

Data Index: 932997 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5135. Min Act: -0.0001

Data Index: 789541 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5774. Min Act: -0.0001

Data Index: 442296 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5945. Min Act: -0.0001

Data Index: 375944 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5267. Min Act: -0.0001

Data Index: 218005 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5718. Min Act: -0.0001

Data Index: 587483 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5519. Min Act: -0.0001

Data Index: 454471 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.6340. Min Act: -0.0001

Data Index: 176710 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5692. Min Act: -0.0001

Data Index: 1220284 (C4 (Web Text))

Max Activating Token Index: 482

Text #19

Max Range: 0.7509. Min Range: -0.7509

Max Act: 0.5627. Min Act: -0.0001

Data Index: 616588 (C4 (Web Text))

Max Activating Token Index: 43