Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3761 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.8105. Min Act: -0.0000

Data Index: 982917 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1472853 (Python Code)

Max Activating Token Index: 719

Text #2

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6975. Min Act: 0.0000

Data Index: 1509605 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1539211 (Python Code)

Max Activating Token Index: 612

Text #4

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1531212 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6397. Min Act: -0.0000

Data Index: 1552021 (Python Code)

Max Activating Token Index: 859

Text #6

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6301. Min Act: -0.0000

Data Index: 1491629 (Python Code)

Max Activating Token Index: 36

Text #7

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6052. Min Act: 0.0000

Data Index: 1606361 (Python Code)

Max Activating Token Index: 392

Text #8

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1283062 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1515835 (Python Code)

Max Activating Token Index: 153

Text #10

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1385410 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.6261. Min Act: -0.0000

Data Index: 508591 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1500815 (Python Code)

Max Activating Token Index: 694

Text #13

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1381848 (Python Code)

Max Activating Token Index: 300

Text #14

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1376890 (Python Code)

Max Activating Token Index: 459

Text #15

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1421986 (Python Code)

Max Activating Token Index: 313

Text #16

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1470698 (Python Code)

Max Activating Token Index: 342

Text #17

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1444615 (Python Code)

Max Activating Token Index: 535

Text #18

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1360294 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 0.8105. Min Range: -0.8105

Max Act: 0.5395. Min Act: -0.0000

Data Index: 1605750 (Python Code)

Max Activating Token Index: 950