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

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

Neuron 379 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: 3.7751. Min Range: -3.7751

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1573145 (Python Code)

Max Activating Token Index: 833

Text #1

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.7178. Min Act: -0.1700

Data Index: 1443286 (Python Code)

Max Activating Token Index: 833

Text #2

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.7014. Min Act: -0.1700

Data Index: 1461321 (Python Code)

Max Activating Token Index: 61

Text #3

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.6889. Min Act: -0.1700

Data Index: 1532584 (Python Code)

Max Activating Token Index: 389

Text #4

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.6404. Min Act: -0.1700

Data Index: 1618342 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.6363. Min Act: -0.1700

Data Index: 1593735 (Python Code)

Max Activating Token Index: 879

Text #6

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.6068. Min Act: -0.1700

Data Index: 1502369 (Python Code)

Max Activating Token Index: 809

Text #7

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5924. Min Act: -0.1700

Data Index: 1455053 (Python Code)

Max Activating Token Index: 584

Text #8

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1426864 (Python Code)

Max Activating Token Index: 430

Text #9

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5831. Min Act: -0.1700

Data Index: 1486050 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5678. Min Act: -0.1700

Data Index: 1651600 (Python Code)

Max Activating Token Index: 963

Text #11

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5690. Min Act: -0.1700

Data Index: 1528607 (Python Code)

Max Activating Token Index: 420

Text #12

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5833. Min Act: -0.1700

Data Index: 1607754 (Python Code)

Max Activating Token Index: 711

Text #13

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5425. Min Act: -0.1700

Data Index: 1575441 (Python Code)

Max Activating Token Index: 773

Text #14

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5423. Min Act: -0.1700

Data Index: 1652562 (Python Code)

Max Activating Token Index: 495

Text #15

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5389. Min Act: -0.1700

Data Index: 1650591 (Python Code)

Max Activating Token Index: 520

Text #16

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5247. Min Act: -0.1700

Data Index: 1434150 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5454. Min Act: -0.1700

Data Index: 1419948 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5247. Min Act: -0.1700

Data Index: 1511103 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 3.7751. Min Range: -3.7751

Max Act: 3.5070. Min Act: -0.1700

Data Index: 1582398 (Python Code)

Max Activating Token Index: 255