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

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

Neuron 832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3079. Min Range: -2.3079

Max Act: 2.3079. Min Act: -0.0000

Data Index: 1597541 (Python Code)

Max Activating Token Index: 256

Text #1

Max Range: 2.3079. Min Range: -2.3079

Max Act: 2.2216. Min Act: -0.0000

Data Index: 1509221 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 2.3079. Min Range: -2.3079

Max Act: 2.0906. Min Act: -0.0000

Data Index: 1584871 (Python Code)

Max Activating Token Index: 67

Text #3

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.8644. Min Act: -0.0000

Data Index: 1539815 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.8771. Min Act: -0.0000

Data Index: 1368145 (Python Code)

Max Activating Token Index: 266

Text #5

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.8787. Min Act: -0.0000

Data Index: 1531280 (Python Code)

Max Activating Token Index: 384

Text #6

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.8681. Min Act: -0.0000

Data Index: 1643401 (Python Code)

Max Activating Token Index: 909

Text #7

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.7924. Min Act: -0.0000

Data Index: 1421523 (Python Code)

Max Activating Token Index: 377

Text #8

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.7297. Min Act: -0.0000

Data Index: 1610042 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.7348. Min Act: -0.0000

Data Index: 1598661 (Python Code)

Max Activating Token Index: 682

Text #10

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.4978. Min Act: -0.0000

Data Index: 1519279 (Python Code)

Max Activating Token Index: 362

Text #11

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.6273. Min Act: -0.0000

Data Index: 1527289 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.5906. Min Act: -0.0000

Data Index: 1510627 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1480867 (Python Code)

Max Activating Token Index: 289

Text #14

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.5112. Min Act: -0.0000

Data Index: 1444210 (Python Code)

Max Activating Token Index: 76

Text #15

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.4619. Min Act: -0.0000

Data Index: 1573140 (Python Code)

Max Activating Token Index: 772

Text #16

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.7068. Min Act: -0.0000

Data Index: 1530046 (Python Code)

Max Activating Token Index: 1001

Text #17

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.7239. Min Act: -0.0000

Data Index: 1457078 (Python Code)

Max Activating Token Index: 227

Text #18

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.6531. Min Act: -0.0000

Data Index: 1412641 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 2.3079. Min Range: -2.3079

Max Act: 1.4771. Min Act: -0.0000

Data Index: 1392461 (Python Code)

Max Activating Token Index: 233