Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3400 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1091012 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.9147. Min Act: -0.0000

Data Index: 588662 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.9022. Min Act: -0.0000

Data Index: 146850 (C4 (Web Text))

Max Activating Token Index: 535

Text #3

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.8692. Min Act: -0.0000

Data Index: 1137227 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7978. Min Act: -0.0000

Data Index: 66976 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.8218. Min Act: -0.0000

Data Index: 1043498 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7938. Min Act: -0.0000

Data Index: 657960 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7616. Min Act: -0.0000

Data Index: 634022 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7518. Min Act: -0.0000

Data Index: 841090 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1107134 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7865. Min Act: -0.0000

Data Index: 29831 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7103. Min Act: -0.0000

Data Index: 391594 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7200. Min Act: -0.0000

Data Index: 179042 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7367. Min Act: -0.0000

Data Index: 1121865 (C4 (Web Text))

Max Activating Token Index: 120

Text #14

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.7216. Min Act: 0.0000

Data Index: 461344 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.6940. Min Act: -0.0000

Data Index: 202348 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.6764. Min Act: -0.0000

Data Index: 1077744 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.6761. Min Act: 0.0000

Data Index: 1044888 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.6412. Min Act: -0.0000

Data Index: 510441 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.9302. Min Range: -0.9302

Max Act: 0.6742. Min Act: -0.0000

Data Index: 276221 (C4 (Web Text))

Max Activating Token Index: 446