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

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

Neuron 5653 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4601. Min Range: -4.4601

Max Act: 4.2063. Min Act: -0.0000

Data Index: 1512403 (Python Code)

Max Activating Token Index: 965

Text #1

Max Range: 4.4601. Min Range: -4.4601

Max Act: 4.1570. Min Act: -0.0000

Data Index: 1532473 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 4.4601. Min Range: -4.4601

Max Act: 4.1169. Min Act: -0.0000

Data Index: 1396421 (Python Code)

Max Activating Token Index: 608

Text #3

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.9055. Min Act: -0.0000

Data Index: 1526673 (Python Code)

Max Activating Token Index: 743

Text #4

Max Range: 4.4601. Min Range: -4.4601

Max Act: 4.0886. Min Act: -0.0000

Data Index: 1418162 (Python Code)

Max Activating Token Index: 913

Text #5

Max Range: 4.4601. Min Range: -4.4601

Max Act: 4.4601. Min Act: -0.0000

Data Index: 1367665 (Python Code)

Max Activating Token Index: 980

Text #6

Max Range: 4.4601. Min Range: -4.4601

Max Act: 4.0089. Min Act: -0.0000

Data Index: 1365296 (Python Code)

Max Activating Token Index: 911

Text #7

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.5983. Min Act: -0.0000

Data Index: 1630260 (Python Code)

Max Activating Token Index: 777

Text #8

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.7850. Min Act: -0.0000

Data Index: 1511408 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.7346. Min Act: -0.0000

Data Index: 1453008 (Python Code)

Max Activating Token Index: 989

Text #10

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.8490. Min Act: -0.0000

Data Index: 1534942 (Python Code)

Max Activating Token Index: 883

Text #11

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.7281. Min Act: -0.0000

Data Index: 1383193 (Python Code)

Max Activating Token Index: 993

Text #12

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.3496. Min Act: -0.0000

Data Index: 1524873 (Python Code)

Max Activating Token Index: 884

Text #13

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.3352. Min Act: -0.0000

Data Index: 1601289 (Python Code)

Max Activating Token Index: 956

Text #14

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.6115. Min Act: -0.0000

Data Index: 1499258 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.3121. Min Act: -0.0000

Data Index: 1466960 (Python Code)

Max Activating Token Index: 1011

Text #16

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.1076. Min Act: -0.0000

Data Index: 1576270 (Python Code)

Max Activating Token Index: 833

Text #17

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.1435. Min Act: -0.0000

Data Index: 1463295 (Python Code)

Max Activating Token Index: 918

Text #18

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.5611. Min Act: -0.0000

Data Index: 1382556 (Python Code)

Max Activating Token Index: 424

Text #19

Max Range: 4.4601. Min Range: -4.4601

Max Act: 3.5624. Min Act: -0.0000

Data Index: 1525122 (Python Code)

Max Activating Token Index: 934