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

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

Neuron 3522 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.5924. Min Act: -0.0000

Data Index: 1395303 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.6920. Min Act: -0.0000

Data Index: 1452370 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.4585. Min Act: -0.0000

Data Index: 1361379 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1480. Min Act: -0.0000

Data Index: 1496471 (Python Code)

Max Activating Token Index: 884

Text #4

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.2669. Min Act: -0.0000

Data Index: 1497527 (Python Code)

Max Activating Token Index: 665

Text #5

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.2253. Min Act: -0.0000

Data Index: 1455642 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1007. Min Act: -0.0000

Data Index: 1644759 (Python Code)

Max Activating Token Index: 867

Text #7

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.3165. Min Act: -0.0000

Data Index: 1459994 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1969. Min Act: -0.0000

Data Index: 1426941 (Python Code)

Max Activating Token Index: 536

Text #9

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1763. Min Act: -0.0000

Data Index: 1648125 (Python Code)

Max Activating Token Index: 748

Text #10

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1728. Min Act: -0.0000

Data Index: 1605525 (Python Code)

Max Activating Token Index: 530

Text #11

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.0314. Min Act: -0.0000

Data Index: 1499729 (Python Code)

Max Activating Token Index: 465

Text #12

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1021. Min Act: -0.0000

Data Index: 1570452 (Python Code)

Max Activating Token Index: 469

Text #13

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.0808. Min Act: -0.0000

Data Index: 1481239 (Python Code)

Max Activating Token Index: 558

Text #14

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.1951. Min Act: -0.0000

Data Index: 1470801 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 2.6920. Min Range: -2.6920

Max Act: 1.9748. Min Act: -0.0000

Data Index: 1525480 (Python Code)

Max Activating Token Index: 831

Text #16

Max Range: 2.6920. Min Range: -2.6920

Max Act: 1.9764. Min Act: -0.0000

Data Index: 1419763 (Python Code)

Max Activating Token Index: 987

Text #17

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.0580. Min Act: -0.0000

Data Index: 1606740 (Python Code)

Max Activating Token Index: 971

Text #18

Max Range: 2.6920. Min Range: -2.6920

Max Act: 2.0311. Min Act: -0.0000

Data Index: 1422639 (Python Code)

Max Activating Token Index: 917

Text #19

Max Range: 2.6920. Min Range: -2.6920

Max Act: 1.8856. Min Act: -0.0000

Data Index: 1598852 (Python Code)

Max Activating Token Index: 977