Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1660 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.7192. Min Act: -0.1694

Data Index: 1602081 (Python Code)

Max Activating Token Index: 851

Text #1

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6498. Min Act: -0.1700

Data Index: 1625697 (Python Code)

Max Activating Token Index: 916

Text #2

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6699. Min Act: -0.1700

Data Index: 620871 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6682. Min Act: -0.1700

Data Index: 1427413 (Python Code)

Max Activating Token Index: 266

Text #4

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1444288 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6114. Min Act: -0.1700

Data Index: 1438064 (Python Code)

Max Activating Token Index: 597

Text #6

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6647. Min Act: -0.1700

Data Index: 1637400 (Python Code)

Max Activating Token Index: 290

Text #7

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6237. Min Act: -0.1700

Data Index: 1619542 (Python Code)

Max Activating Token Index: 849

Text #8

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6212. Min Act: -0.1700

Data Index: 1487816 (Python Code)

Max Activating Token Index: 199

Text #9

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6272. Min Act: -0.1700

Data Index: 1490274 (Python Code)

Max Activating Token Index: 766

Text #10

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.6018. Min Act: -0.1700

Data Index: 1591270 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5835. Min Act: -0.1700

Data Index: 1618862 (Python Code)

Max Activating Token Index: 487

Text #12

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5752. Min Act: -0.1700

Data Index: 1625393 (Python Code)

Max Activating Token Index: 511

Text #13

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5825. Min Act: -0.1700

Data Index: 1608688 (Python Code)

Max Activating Token Index: 15

Text #14

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5492. Min Act: -0.1700

Data Index: 1454724 (Python Code)

Max Activating Token Index: 859

Text #15

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5283. Min Act: -0.1700

Data Index: 1552385 (Python Code)

Max Activating Token Index: 368

Text #16

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5425. Min Act: -0.1700

Data Index: 1560233 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5065. Min Act: -0.1700

Data Index: 1518806 (Python Code)

Max Activating Token Index: 411

Text #18

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.5166. Min Act: -0.1700

Data Index: 1635029 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 3.7192. Min Range: -3.7192

Max Act: 3.4782. Min Act: -0.1700

Data Index: 1632772 (Python Code)

Max Activating Token Index: 142