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

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

Neuron 349 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.2513. Min Act: -0.0000

Data Index: 130716 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.2056. Min Act: -0.0000

Data Index: 1606950 (Python Code)

Max Activating Token Index: 458

Text #2

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.2442. Min Act: -0.0000

Data Index: 1428775 (Python Code)

Max Activating Token Index: 433

Text #3

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.1586. Min Act: -0.0000

Data Index: 1545438 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.1305. Min Act: -0.0000

Data Index: 1387904 (Python Code)

Max Activating Token Index: 79

Text #5

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.1561. Min Act: -0.0000

Data Index: 1513733 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1553007 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1452075 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.0609. Min Act: -0.0000

Data Index: 1485687 (Python Code)

Max Activating Token Index: 724

Text #9

Max Range: 1.2513. Min Range: -1.2513

Max Act: 1.0413. Min Act: -0.0000

Data Index: 1388766 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1461066 (Python Code)

Max Activating Token Index: 719

Text #11

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1381192 (Python Code)

Max Activating Token Index: 829

Text #12

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1533451 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9422. Min Act: -0.0000

Data Index: 1424747 (Python Code)

Max Activating Token Index: 571

Text #14

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9488. Min Act: -0.0000

Data Index: 1603526 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1415690 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.8821. Min Act: -0.0000

Data Index: 1272095 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.8168. Min Act: -0.0000

Data Index: 1401514 (Python Code)

Max Activating Token Index: 864

Text #18

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1455323 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 1.2513. Min Range: -1.2513

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1558864 (Python Code)

Max Activating Token Index: 90