Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1610 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5571. Min Act: 0.0002

Data Index: 326048 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5356. Min Act: 0.0000

Data Index: 886626 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1340843 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5188. Min Act: 0.0002

Data Index: 753473 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.5138. Min Act: -0.0000

Data Index: 112892 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4882. Min Act: 0.0001

Data Index: 860106 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4808. Min Act: 0.0000

Data Index: 1495230 (Python Code)

Max Activating Token Index: 926

Text #7

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1403307 (Python Code)

Max Activating Token Index: 604

Text #8

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4747. Min Act: 0.0000

Data Index: 502039 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4423. Min Act: -0.0000

Data Index: 1460360 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1029467 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4456. Min Act: -0.0000

Data Index: 389807 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4288. Min Act: 0.0001

Data Index: 1495107 (Python Code)

Max Activating Token Index: 268

Text #13

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4708. Min Act: -0.0000

Data Index: 108961 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4502. Min Act: 0.0000

Data Index: 388685 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4657. Min Act: -0.0000

Data Index: 794075 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4522. Min Act: 0.0000

Data Index: 704051 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4501. Min Act: -0.0000

Data Index: 1046825 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1521141 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 0.5571. Min Range: -0.5571

Max Act: 0.4379. Min Act: -0.0000

Data Index: 712323 (C4 (Web Text))

Max Activating Token Index: 455