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

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

Neuron 3937 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: 0.6642. Min Range: -0.6642

Max Act: 0.6527. Min Act: -0.0001

Data Index: 8798 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6475. Min Act: -0.0001

Data Index: 864994 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6642. Min Act: -0.0001

Data Index: 904798 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5867. Min Act: -0.0001

Data Index: 356555 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.6008. Min Act: -0.0001

Data Index: 237859 (C4 (Web Text))

Max Activating Token Index: 122

Text #5

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5623. Min Act: -0.0001

Data Index: 1101459 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5914. Min Act: -0.0001

Data Index: 524540 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5889. Min Act: -0.0001

Data Index: 756085 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5598. Min Act: -0.0001

Data Index: 373360 (C4 (Web Text))

Max Activating Token Index: 7

Text #9

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5813. Min Act: -0.0001

Data Index: 187667 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5573. Min Act: -0.0001

Data Index: 564378 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5655. Min Act: -0.0001

Data Index: 862645 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5541. Min Act: -0.0001

Data Index: 175349 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5404. Min Act: -0.0001

Data Index: 227750 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5514. Min Act: -0.0001

Data Index: 1181764 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5405. Min Act: -0.0001

Data Index: 678526 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5347. Min Act: -0.0001

Data Index: 346392 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5156. Min Act: -0.0001

Data Index: 824273 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.5264. Min Act: -0.0001

Data Index: 1130814 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.6642. Min Range: -0.6642

Max Act: 0.4937. Min Act: -0.0001

Data Index: 1006592 (C4 (Web Text))

Max Activating Token Index: 881