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

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

Neuron 2037 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: 3.8501. Min Range: -3.8501

Max Act: 3.8501. Min Act: -0.1700

Data Index: 1546345 (Python Code)

Max Activating Token Index: 167

Text #1

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.8122. Min Act: -0.1700

Data Index: 1449138 (Python Code)

Max Activating Token Index: 656

Text #2

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.8013. Min Act: -0.1700

Data Index: 1372335 (Python Code)

Max Activating Token Index: 925

Text #3

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6168. Min Act: -0.1700

Data Index: 1471804 (Python Code)

Max Activating Token Index: 77

Text #4

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5931. Min Act: -0.1700

Data Index: 1560116 (Python Code)

Max Activating Token Index: 49

Text #5

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5794. Min Act: -0.1700

Data Index: 1482995 (Python Code)

Max Activating Token Index: 784

Text #6

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5434. Min Act: -0.1700

Data Index: 1476017 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5790. Min Act: -0.1700

Data Index: 1464050 (Python Code)

Max Activating Token Index: 542

Text #8

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5410. Min Act: -0.1700

Data Index: 4347 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5397. Min Act: -0.1700

Data Index: 1546620 (Python Code)

Max Activating Token Index: 533

Text #10

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5490. Min Act: -0.1700

Data Index: 1648537 (Python Code)

Max Activating Token Index: 144

Text #11

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5433. Min Act: -0.1700

Data Index: 1393472 (Python Code)

Max Activating Token Index: 372

Text #12

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5107. Min Act: -0.1700

Data Index: 112305 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5196. Min Act: -0.1700

Data Index: 1554422 (Python Code)

Max Activating Token Index: 689

Text #14

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5511. Min Act: -0.1700

Data Index: 1381520 (Python Code)

Max Activating Token Index: 632

Text #15

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5079. Min Act: -0.1699

Data Index: 1561793 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.4920. Min Act: -0.1700

Data Index: 1628209 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.4915. Min Act: -0.1700

Data Index: 1433991 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.4831. Min Act: -0.1700

Data Index: 1571312 (Python Code)

Max Activating Token Index: 78

Text #19

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.4844. Min Act: -0.1700

Data Index: 1390856 (Python Code)

Max Activating Token Index: 114