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

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

Neuron 928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1182082 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1077216 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8311. Min Act: -0.0000

Data Index: 155211 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8496. Min Act: -0.0001

Data Index: 467349 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8374. Min Act: -0.0000

Data Index: 227683 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8262. Min Act: -0.0001

Data Index: 780607 (C4 (Web Text))

Max Activating Token Index: 338

Text #6

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8095. Min Act: -0.0001

Data Index: 768855 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.8148. Min Act: -0.0000

Data Index: 880422 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7978. Min Act: -0.0000

Data Index: 846615 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7737. Min Act: -0.0001

Data Index: 388042 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7585. Min Act: -0.0000

Data Index: 16491 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7299. Min Act: -0.0001

Data Index: 33347 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7309. Min Act: -0.0000

Data Index: 222516 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7724. Min Act: -0.0000

Data Index: 1098239 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7409. Min Act: -0.0000

Data Index: 1278458 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7314. Min Act: -0.0000

Data Index: 97150 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7589. Min Act: -0.0001

Data Index: 761863 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1139895 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7332. Min Act: -0.0000

Data Index: 440915 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.8680. Min Range: -0.8680

Max Act: 0.7275. Min Act: -0.0001

Data Index: 64596 (C4 (Web Text))

Max Activating Token Index: 1022