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

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

Neuron 3465 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0092. Min Range: -1.0092

Max Act: 1.0092. Min Act: -0.0001

Data Index: 1307270 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.9305. Min Act: -0.0001

Data Index: 688626 (C4 (Web Text))

Max Activating Token Index: 180

Text #2

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.9059. Min Act: -0.0002

Data Index: 1196440 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.8573. Min Act: -0.0001

Data Index: 1316088 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7557. Min Act: -0.0001

Data Index: 796552 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7555. Min Act: -0.0002

Data Index: 633742 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7223. Min Act: -0.0001

Data Index: 697662 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7427. Min Act: -0.0002

Data Index: 269268 (C4 (Web Text))

Max Activating Token Index: 642

Text #8

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7350. Min Act: -0.0002

Data Index: 345347 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7096. Min Act: -0.0002

Data Index: 1278510 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6847. Min Act: -0.0002

Data Index: 414350 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6832. Min Act: -0.0001

Data Index: 767000 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6814. Min Act: -0.0002

Data Index: 437488 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7131. Min Act: -0.0002

Data Index: 692138 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7001. Min Act: -0.0002

Data Index: 927588 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6585. Min Act: -0.0001

Data Index: 583809 (C4 (Web Text))

Max Activating Token Index: 728

Text #16

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6548. Min Act: -0.0002

Data Index: 519215 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.7037. Min Act: -0.0001

Data Index: 584774 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6167. Min Act: -0.0001

Data Index: 1348876 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 1.0092. Min Range: -1.0092

Max Act: 0.6760. Min Act: -0.0001

Data Index: 387152 (C4 (Web Text))

Max Activating Token Index: 675