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

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

Neuron 3164 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: 0.6731. Min Range: -0.6731

Max Act: 0.6526. Min Act: -0.0001

Data Index: 361462 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6717. Min Act: -0.0001

Data Index: 1138982 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6538. Min Act: -0.0001

Data Index: 979010 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6631. Min Act: -0.0001

Data Index: 1038130 (C4 (Web Text))

Max Activating Token Index: 446

Text #4

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6381. Min Act: -0.0001

Data Index: 333452 (C4 (Web Text))

Max Activating Token Index: 329

Text #5

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6553. Min Act: -0.0001

Data Index: 601319 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6056. Min Act: -0.0001

Data Index: 986327 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6245. Min Act: -0.0001

Data Index: 583343 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6731. Min Act: -0.0001

Data Index: 386995 (C4 (Web Text))

Max Activating Token Index: 716

Text #9

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.6120. Min Act: -0.0001

Data Index: 692974 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5991. Min Act: -0.0001

Data Index: 45638 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5654. Min Act: -0.0001

Data Index: 1181310 (C4 (Web Text))

Max Activating Token Index: 151

Text #12

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5527. Min Act: -0.0001

Data Index: 385249 (C4 (Web Text))

Max Activating Token Index: 886

Text #13

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.5054. Min Act: -0.0001

Data Index: 359184 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4509. Min Act: -0.0001

Data Index: 899711 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4896. Min Act: -0.0001

Data Index: 550493 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4594. Min Act: -0.0001

Data Index: 448262 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4474. Min Act: -0.0001

Data Index: 70420 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4475. Min Act: -0.0001

Data Index: 294080 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.6731. Min Range: -0.6731

Max Act: 0.4454. Min Act: -0.0001

Data Index: 1208990 (C4 (Web Text))

Max Activating Token Index: 381