Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1554 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.8211. Min Act: -0.1700

Data Index: 967662 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.7116. Min Act: -0.1700

Data Index: 724423 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.6803. Min Act: -0.1700

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 840

Text #3

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.6646. Min Act: -0.1700

Data Index: 495481 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.6020. Min Act: -0.1700

Data Index: 1442808 (Python Code)

Max Activating Token Index: 931

Text #5

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5237. Min Act: -0.1700

Data Index: 1603564 (Python Code)

Max Activating Token Index: 239

Text #6

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5550. Min Act: -0.1700

Data Index: 1291743 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5550. Min Act: -0.1700

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5394. Min Act: -0.1700

Data Index: 78749 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5237. Min Act: -0.1700

Data Index: 1550955 (Python Code)

Max Activating Token Index: 91

Text #10

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5080. Min Act: -0.1700

Data Index: 1526256 (Python Code)

Max Activating Token Index: 61

Text #11

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5080. Min Act: -0.1700

Data Index: 1591445 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4610. Min Act: -0.1700

Data Index: 1589099 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4767. Min Act: -0.1699

Data Index: 1638169 (Python Code)

Max Activating Token Index: 941

Text #14

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1466972 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1531358 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.5080. Min Act: -0.1700

Data Index: 1056720 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1417387 (Python Code)

Max Activating Token Index: 88

Text #18

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1599658 (Python Code)

Max Activating Token Index: 88

Text #19

Max Range: 3.8211. Min Range: -3.8211

Max Act: 3.4454. Min Act: -0.1700

Data Index: 1474737 (Python Code)

Max Activating Token Index: 62