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

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

Neuron 3183 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.5838. Min Act: -0.0000

Data Index: 1584783 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4684. Min Act: -0.0000

Data Index: 1444530 (Python Code)

Max Activating Token Index: 797

Text #2

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4857. Min Act: -0.0000

Data Index: 1499369 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3838. Min Act: -0.0000

Data Index: 1480120 (Python Code)

Max Activating Token Index: 986

Text #4

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4645. Min Act: -0.0000

Data Index: 1564449 (Python Code)

Max Activating Token Index: 8

Text #5

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1448865 (Python Code)

Max Activating Token Index: 512

Text #6

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4197. Min Act: -0.0000

Data Index: 1564869 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4102. Min Act: -0.0000

Data Index: 1454208 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.4883. Min Act: -0.0000

Data Index: 1432205 (Python Code)

Max Activating Token Index: 301

Text #9

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3168. Min Act: -0.0000

Data Index: 1614249 (Python Code)

Max Activating Token Index: 489

Text #10

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1512678 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3104. Min Act: -0.0000

Data Index: 1494792 (Python Code)

Max Activating Token Index: 513

Text #12

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3131. Min Act: -0.0000

Data Index: 1522679 (Python Code)

Max Activating Token Index: 363

Text #13

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3110. Min Act: -0.0000

Data Index: 291758 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1620002 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.3030. Min Act: -0.0000

Data Index: 1329190 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2664. Min Act: -0.0000

Data Index: 1536250 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1389753 (Python Code)

Max Activating Token Index: 127

Text #18

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2417. Min Act: -0.0000

Data Index: 1383379 (Python Code)

Max Activating Token Index: 406

Text #19

Max Range: 1.5838. Min Range: -1.5838

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1381269 (Python Code)

Max Activating Token Index: 981