Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.6748. Min Act: -0.0001

Data Index: 1587807 (Python Code)

Max Activating Token Index: 634

Text #1

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.6348. Min Act: -0.0001

Data Index: 1479925 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.6047. Min Act: -0.0001

Data Index: 1596185 (Python Code)

Max Activating Token Index: 386

Text #3

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.3443. Min Act: -0.0001

Data Index: 1509413 (Python Code)

Max Activating Token Index: 751

Text #4

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.6558. Min Act: -0.0001

Data Index: 1483317 (Python Code)

Max Activating Token Index: 113

Text #5

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.1729. Min Act: -0.0001

Data Index: 1503094 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.3045. Min Act: -0.0001

Data Index: 1654044 (Python Code)

Max Activating Token Index: 104

Text #7

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.4680. Min Act: -0.0001

Data Index: 1518191 (Python Code)

Max Activating Token Index: 518

Text #8

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.2792. Min Act: -0.0001

Data Index: 1489383 (Python Code)

Max Activating Token Index: 105

Text #9

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.0826. Min Act: -0.0001

Data Index: 1372597 (Python Code)

Max Activating Token Index: 744

Text #10

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.0261. Min Act: -0.0001

Data Index: 1524602 (Python Code)

Max Activating Token Index: 590

Text #11

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.3656. Min Act: -0.0001

Data Index: 1563706 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.1543. Min Act: -0.0001

Data Index: 1371524 (Python Code)

Max Activating Token Index: 764

Text #13

Max Range: 5.6748. Min Range: -5.6748

Max Act: 4.9818. Min Act: -0.0001

Data Index: 1502725 (Python Code)

Max Activating Token Index: 699

Text #14

Max Range: 5.6748. Min Range: -5.6748

Max Act: 4.9764. Min Act: -0.0001

Data Index: 1460700 (Python Code)

Max Activating Token Index: 240

Text #15

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.3153. Min Act: -0.0001

Data Index: 1602307 (Python Code)

Max Activating Token Index: 830

Text #16

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.3099. Min Act: -0.0001

Data Index: 1364936 (Python Code)

Max Activating Token Index: 108

Text #17

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.3106. Min Act: -0.0001

Data Index: 1639697 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 5.6748. Min Range: -5.6748

Max Act: 5.1258. Min Act: -0.0001

Data Index: 1549779 (Python Code)

Max Activating Token Index: 411

Text #19

Max Range: 5.6748. Min Range: -5.6748

Max Act: 4.9142. Min Act: -0.0001

Data Index: 1638486 (Python Code)

Max Activating Token Index: 620