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

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

Neuron 3690 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7903. Min Act: -0.0001

Data Index: 59597 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1273595 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6002. Min Act: -0.0001

Data Index: 182517 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5920. Min Act: -0.0001

Data Index: 44871 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5347. Min Act: -0.0001

Data Index: 1227980 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5083. Min Act: -0.0001

Data Index: 1160726 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4935. Min Act: -0.0001

Data Index: 79636 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5093. Min Act: -0.0001

Data Index: 1024064 (C4 (Web Text))

Max Activating Token Index: 531

Text #8

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.5226. Min Act: -0.0001

Data Index: 249218 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4875. Min Act: -0.0001

Data Index: 933713 (C4 (Web Text))

Max Activating Token Index: 304

Text #10

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4658. Min Act: -0.0001

Data Index: 707823 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4469. Min Act: -0.0001

Data Index: 1337856 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4921. Min Act: -0.0001

Data Index: 598553 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4275. Min Act: -0.0001

Data Index: 704896 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4861. Min Act: -0.0001

Data Index: 1054841 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4630. Min Act: -0.0001

Data Index: 190634 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4917. Min Act: -0.0001

Data Index: 185993 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4434. Min Act: -0.0001

Data Index: 292633 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4735. Min Act: -0.0001

Data Index: 1282084 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.4684. Min Act: -0.0001

Data Index: 869682 (C4 (Web Text))

Max Activating Token Index: 285