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

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

Neuron 4829 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: 3.8929. Min Range: -3.8929

Max Act: 3.8929. Min Act: -0.0000

Data Index: 1528103 (Python Code)

Max Activating Token Index: 711

Text #1

Max Range: 3.8929. Min Range: -3.8929

Max Act: 3.3689. Min Act: -0.0000

Data Index: 1589080 (Python Code)

Max Activating Token Index: 908

Text #2

Max Range: 3.8929. Min Range: -3.8929

Max Act: 3.2665. Min Act: -0.0000

Data Index: 1462372 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.6488. Min Act: -0.0000

Data Index: 1538840 (Python Code)

Max Activating Token Index: 807

Text #4

Max Range: 3.8929. Min Range: -3.8929

Max Act: 3.1588. Min Act: -0.0000

Data Index: 1492063 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.8707. Min Act: -0.0000

Data Index: 1535460 (Python Code)

Max Activating Token Index: 727

Text #6

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.7978. Min Act: -0.0000

Data Index: 1655881 (Python Code)

Max Activating Token Index: 435

Text #7

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.6478. Min Act: -0.0000

Data Index: 1560202 (Python Code)

Max Activating Token Index: 439

Text #8

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.4928. Min Act: -0.0000

Data Index: 1412189 (Python Code)

Max Activating Token Index: 829

Text #9

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.8007. Min Act: -0.0000

Data Index: 1546842 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.8268. Min Act: -0.0000

Data Index: 759538 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.9466. Min Act: -0.0000

Data Index: 1512679 (Python Code)

Max Activating Token Index: 662

Text #12

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.6351. Min Act: -0.0000

Data Index: 1491901 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.8469. Min Act: -0.0000

Data Index: 1623082 (Python Code)

Max Activating Token Index: 592

Text #14

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.8691. Min Act: -0.0000

Data Index: 1367349 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.5748. Min Act: -0.0000

Data Index: 1170742 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.7032. Min Act: -0.0000

Data Index: 327359 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.8215. Min Act: -0.0000

Data Index: 866019 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.6952. Min Act: -0.0000

Data Index: 1371279 (Python Code)

Max Activating Token Index: 167

Text #19

Max Range: 3.8929. Min Range: -3.8929

Max Act: 2.4264. Min Act: -0.0000

Data Index: 1441118 (Python Code)

Max Activating Token Index: 111