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

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

Neuron 2699 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4297. Min Range: -1.4297

Max Act: 1.4297. Min Act: -0.0000

Data Index: 1406441 (Python Code)

Max Activating Token Index: 203

Text #1

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1282995 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.7360. Min Act: -0.0000

Data Index: 1585120 (Python Code)

Max Activating Token Index: 781

Text #3

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.7811. Min Act: -0.0000

Data Index: 2166 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.7179. Min Act: -0.0000

Data Index: 1425209 (Python Code)

Max Activating Token Index: 574

Text #5

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6792. Min Act: -0.0000

Data Index: 1450351 (Python Code)

Max Activating Token Index: 332

Text #6

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.7229. Min Act: -0.0000

Data Index: 393473 (C4 (Web Text))

Max Activating Token Index: 78

Text #7

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1453844 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1587625 (Python Code)

Max Activating Token Index: 191

Text #9

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6964. Min Act: -0.0000

Data Index: 1612278 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6270. Min Act: -0.0000

Data Index: 1512127 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1494489 (Python Code)

Max Activating Token Index: 726

Text #12

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1582871 (Python Code)

Max Activating Token Index: 495

Text #13

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6755. Min Act: -0.0000

Data Index: 492037 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1591698 (Python Code)

Max Activating Token Index: 390

Text #15

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1528669 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6894. Min Act: -0.0000

Data Index: 1582447 (Python Code)

Max Activating Token Index: 353

Text #17

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6162. Min Act: -0.0000

Data Index: 1592216 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.6526. Min Act: -0.0000

Data Index: 1623655 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 1.4297. Min Range: -1.4297

Max Act: 0.5719. Min Act: -0.0000

Data Index: 893824 (C4 (Web Text))

Max Activating Token Index: 278