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

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

Neuron 1613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0241. Min Range: -1.0241

Max Act: 1.0241. Min Act: -0.0001

Data Index: 1636224 (Python Code)

Max Activating Token Index: 477

Text #1

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.9662. Min Act: -0.0002

Data Index: 1532824 (Python Code)

Max Activating Token Index: 17

Text #2

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.9437. Min Act: -0.0001

Data Index: 1384156 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1645319 (Python Code)

Max Activating Token Index: 18

Text #4

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1404716 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8364. Min Act: -0.0001

Data Index: 1541288 (Python Code)

Max Activating Token Index: 25

Text #6

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8337. Min Act: -0.0001

Data Index: 1532048 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.8517. Min Act: -0.0001

Data Index: 1380442 (Python Code)

Max Activating Token Index: 34

Text #8

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1628455 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7731. Min Act: -0.0001

Data Index: 1513568 (Python Code)

Max Activating Token Index: 34

Text #10

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7874. Min Act: -0.0001

Data Index: 1406731 (Python Code)

Max Activating Token Index: 820

Text #11

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.6855. Min Act: -0.0001

Data Index: 1412282 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1458158 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7908. Min Act: -0.0001

Data Index: 1518579 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1592645 (Python Code)

Max Activating Token Index: 64

Text #15

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7419. Min Act: -0.0001

Data Index: 1542976 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7352. Min Act: -0.0001

Data Index: 1411046 (Python Code)

Max Activating Token Index: 25

Text #17

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7284. Min Act: -0.0001

Data Index: 1535512 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1537230 (Python Code)

Max Activating Token Index: 114

Text #19

Max Range: 1.0241. Min Range: -1.0241

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1450521 (Python Code)

Max Activating Token Index: 30