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

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

Neuron 61 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.9800. Min Act: -0.0001

Data Index: 1537058 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.9653. Min Act: -0.0001

Data Index: 1549690 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.9448. Min Act: -0.0001

Data Index: 1481241 (Python Code)

Max Activating Token Index: 199

Text #3

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8976. Min Act: -0.0001

Data Index: 1434177 (Python Code)

Max Activating Token Index: 443

Text #4

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8691. Min Act: -0.0001

Data Index: 1570744 (Python Code)

Max Activating Token Index: 680

Text #5

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8792. Min Act: -0.0001

Data Index: 1493319 (Python Code)

Max Activating Token Index: 483

Text #6

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8692. Min Act: -0.0001

Data Index: 1559103 (Python Code)

Max Activating Token Index: 43

Text #7

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8325. Min Act: -0.0001

Data Index: 1515175 (Python Code)

Max Activating Token Index: 467

Text #8

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8440. Min Act: -0.0001

Data Index: 1511942 (Python Code)

Max Activating Token Index: 117

Text #9

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8122. Min Act: -0.0001

Data Index: 1596545 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8702. Min Act: -0.0001

Data Index: 1378682 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8191. Min Act: -0.0001

Data Index: 1646196 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7798. Min Act: -0.0001

Data Index: 1366485 (Python Code)

Max Activating Token Index: 97

Text #13

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.8013. Min Act: -0.0001

Data Index: 1443367 (Python Code)

Max Activating Token Index: 97

Text #14

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7699. Min Act: -0.0001

Data Index: 1653026 (Python Code)

Max Activating Token Index: 546

Text #15

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7811. Min Act: -0.0001

Data Index: 1373556 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7526. Min Act: -0.0001

Data Index: 1637654 (Python Code)

Max Activating Token Index: 52

Text #17

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7720. Min Act: -0.0001

Data Index: 1469555 (Python Code)

Max Activating Token Index: 112

Text #18

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7736. Min Act: -0.0001

Data Index: 1394523 (Python Code)

Max Activating Token Index: 356

Text #19

Max Range: 0.9800. Min Range: -0.9800

Max Act: 0.7742. Min Act: -0.0001

Data Index: 1627917 (Python Code)

Max Activating Token Index: 122