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

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

Neuron 1100 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: 5.3134. Min Range: -5.3134

Max Act: 5.3134. Min Act: -0.1700

Data Index: 1654555 (Python Code)

Max Activating Token Index: 881

Text #1

Max Range: 5.3134. Min Range: -5.3134

Max Act: 5.1800. Min Act: -0.1700

Data Index: 1519612 (Python Code)

Max Activating Token Index: 276

Text #2

Max Range: 5.3134. Min Range: -5.3134

Max Act: 5.0660. Min Act: -0.1700

Data Index: 1459126 (Python Code)

Max Activating Token Index: 253

Text #3

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9810. Min Act: -0.1700

Data Index: 1560604 (Python Code)

Max Activating Token Index: 872

Text #4

Max Range: 5.3134. Min Range: -5.3134

Max Act: 5.0409. Min Act: -0.1700

Data Index: 1631506 (Python Code)

Max Activating Token Index: 762

Text #5

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9577. Min Act: -0.1700

Data Index: 377611 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9854. Min Act: -0.1700

Data Index: 1382274 (Python Code)

Max Activating Token Index: 732

Text #7

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9628. Min Act: -0.1700

Data Index: 1467903 (Python Code)

Max Activating Token Index: 999

Text #8

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9052. Min Act: -0.1700

Data Index: 1503077 (Python Code)

Max Activating Token Index: 795

Text #9

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9234. Min Act: -0.1700

Data Index: 1360686 (Python Code)

Max Activating Token Index: 594

Text #10

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8878. Min Act: -0.1700

Data Index: 1573577 (Python Code)

Max Activating Token Index: 408

Text #11

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.9147. Min Act: -0.1700

Data Index: 1567813 (Python Code)

Max Activating Token Index: 407

Text #12

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8670. Min Act: -0.1700

Data Index: 1477015 (Python Code)

Max Activating Token Index: 329

Text #13

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8805. Min Act: -0.1700

Data Index: 1652308 (Python Code)

Max Activating Token Index: 647

Text #14

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8736. Min Act: -0.1700

Data Index: 1455335 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8756. Min Act: -0.1700

Data Index: 1583751 (Python Code)

Max Activating Token Index: 187

Text #16

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8744. Min Act: -0.1700

Data Index: 1494323 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8624. Min Act: -0.1700

Data Index: 1496326 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8424. Min Act: -0.1700

Data Index: 1476448 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 5.3134. Min Range: -5.3134

Max Act: 4.8267. Min Act: -0.1700

Data Index: 1533686 (Python Code)

Max Activating Token Index: 744