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

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

Neuron 3243 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: 5.0879. Min Range: -5.0879

Max Act: 5.0879. Min Act: -0.0000

Data Index: 1559503 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.6129. Min Act: -0.0000

Data Index: 1388795 (Python Code)

Max Activating Token Index: 43

Text #2

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.7379. Min Act: -0.0000

Data Index: 1551606 (Python Code)

Max Activating Token Index: 318

Text #3

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.5423. Min Act: -0.0000

Data Index: 1504340 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.5187. Min Act: -0.0000

Data Index: 1650468 (Python Code)

Max Activating Token Index: 693

Text #5

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.3004. Min Act: -0.0000

Data Index: 1424686 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.4272. Min Act: -0.0000

Data Index: 1575888 (Python Code)

Max Activating Token Index: 819

Text #7

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.0478. Min Act: -0.0000

Data Index: 1527728 (Python Code)

Max Activating Token Index: 428

Text #8

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.3326. Min Act: -0.0000

Data Index: 1372108 (Python Code)

Max Activating Token Index: 311

Text #9

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.3687. Min Act: -0.0000

Data Index: 1471467 (Python Code)

Max Activating Token Index: 321

Text #10

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.1676. Min Act: -0.0000

Data Index: 1449220 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.3224. Min Act: -0.0000

Data Index: 1371925 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 5.0879. Min Range: -5.0879

Max Act: 3.9407. Min Act: -0.0000

Data Index: 1641646 (Python Code)

Max Activating Token Index: 167

Text #13

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.0654. Min Act: -0.0000

Data Index: 1614120 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 5.0879. Min Range: -5.0879

Max Act: 3.7042. Min Act: -0.0000

Data Index: 1576482 (Python Code)

Max Activating Token Index: 342

Text #15

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.0060. Min Act: -0.0000

Data Index: 1460747 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 5.0879. Min Range: -5.0879

Max Act: 3.8562. Min Act: -0.0000

Data Index: 1426141 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.0245. Min Act: -0.0000

Data Index: 1611052 (Python Code)

Max Activating Token Index: 892

Text #18

Max Range: 5.0879. Min Range: -5.0879

Max Act: 3.8316. Min Act: -0.0000

Data Index: 1448055 (Python Code)

Max Activating Token Index: 956

Text #19

Max Range: 5.0879. Min Range: -5.0879

Max Act: 4.0086. Min Act: -0.0000

Data Index: 1476021 (Python Code)

Max Activating Token Index: 61