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

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

Neuron 3401 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: 3.3600. Min Range: -3.3600

Max Act: 3.1705. Min Act: -0.0000

Data Index: 1516945 (Python Code)

Max Activating Token Index: 686

Text #1

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3271. Min Act: -0.0000

Data Index: 1530622 (Python Code)

Max Activating Token Index: 114

Text #2

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.3600. Min Act: -0.0000

Data Index: 1549195 (Python Code)

Max Activating Token Index: 886

Text #3

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0065. Min Act: -0.0000

Data Index: 1485092 (Python Code)

Max Activating Token Index: 384

Text #4

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7888. Min Act: -0.0000

Data Index: 1611885 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0227. Min Act: -0.0000

Data Index: 1476632 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.9944. Min Act: -0.0000

Data Index: 1363215 (Python Code)

Max Activating Token Index: 190

Text #7

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.1634. Min Act: -0.0000

Data Index: 1535181 (Python Code)

Max Activating Token Index: 130

Text #8

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0004. Min Act: -0.0000

Data Index: 1503923 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 3.3600. Min Range: -3.3600

Max Act: 3.0138. Min Act: -0.0000

Data Index: 1445820 (Python Code)

Max Activating Token Index: 781

Text #10

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.9971. Min Act: -0.0000

Data Index: 1627673 (Python Code)

Max Activating Token Index: 330

Text #11

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7373. Min Act: -0.0000

Data Index: 1477272 (Python Code)

Max Activating Token Index: 811

Text #12

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.8416. Min Act: -0.0000

Data Index: 1515312 (Python Code)

Max Activating Token Index: 938

Text #13

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7309. Min Act: -0.0000

Data Index: 1440835 (Python Code)

Max Activating Token Index: 646

Text #14

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.4725. Min Act: -0.0000

Data Index: 1635746 (Python Code)

Max Activating Token Index: 800

Text #15

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7251. Min Act: -0.0000

Data Index: 1492819 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.3162. Min Act: -0.0000

Data Index: 1379905 (Python Code)

Max Activating Token Index: 755

Text #17

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.5620. Min Act: -0.0000

Data Index: 1575491 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.5806. Min Act: -0.0000

Data Index: 1381604 (Python Code)

Max Activating Token Index: 86

Text #19

Max Range: 3.3600. Min Range: -3.3600

Max Act: 2.7952. Min Act: -0.0000

Data Index: 1629539 (Python Code)

Max Activating Token Index: 228