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

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

Neuron 3645 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0001

Data Index: 1542496 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1476951 (Python Code)

Max Activating Token Index: 853

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0644. Min Act: -0.0001

Data Index: 1438274 (Python Code)

Max Activating Token Index: 117

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1397226 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1534108 (Python Code)

Max Activating Token Index: 6

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1025683 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1577526 (Python Code)

Max Activating Token Index: 342

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1199454 (C4 (Web Text))

Max Activating Token Index: 400

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1528239 (Python Code)

Max Activating Token Index: 111

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0559. Min Act: -0.0001

Data Index: 337281 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0572. Min Act: -0.0001

Data Index: 273320 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1172180 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0548. Min Act: -0.0002

Data Index: 390656 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0549. Min Act: -0.0001

Data Index: 212841 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0507. Min Act: -0.0001

Data Index: 5426 (C4 (Web Text))

Max Activating Token Index: 238

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0552. Min Act: -0.0001

Data Index: 900227 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0556. Min Act: -0.0001

Data Index: 509577 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0501. Min Act: -0.0001

Data Index: 77583 (C4 (Web Text))

Max Activating Token Index: 100

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0537. Min Act: -0.0001

Data Index: 886754 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0516. Min Act: -0.0001

Data Index: 607183 (C4 (Web Text))

Max Activating Token Index: 242