Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 452 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6670. Min Act: -0.1700

Data Index: 1642093 (Python Code)

Max Activating Token Index: 836

Text #1

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6670. Min Act: -0.1700

Data Index: 1488800 (Python Code)

Max Activating Token Index: 829

Text #2

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6670. Min Act: -0.1700

Data Index: 1587024 (Python Code)

Max Activating Token Index: 225

Text #3

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.6044. Min Act: -0.1700

Data Index: 1371691 (Python Code)

Max Activating Token Index: 870

Text #4

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5731. Min Act: -0.1700

Data Index: 1554295 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5261. Min Act: -0.1700

Data Index: 1398828 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5418. Min Act: -0.1700

Data Index: 1471263 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5574. Min Act: -0.1700

Data Index: 1577695 (Python Code)

Max Activating Token Index: 473

Text #8

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5261. Min Act: -0.1700

Data Index: 173562 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.5104. Min Act: -0.1700

Data Index: 1583765 (Python Code)

Max Activating Token Index: 491

Text #10

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4634. Min Act: -0.1700

Data Index: 1634365 (Python Code)

Max Activating Token Index: 722

Text #11

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4791. Min Act: -0.1700

Data Index: 1416479 (Python Code)

Max Activating Token Index: 422

Text #12

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1625501 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1614208 (Python Code)

Max Activating Token Index: 59

Text #14

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1511440 (Python Code)

Max Activating Token Index: 703

Text #15

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1459126 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1560669 (Python Code)

Max Activating Token Index: 475

Text #17

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4477. Min Act: -0.1700

Data Index: 1585302 (Python Code)

Max Activating Token Index: 907

Text #18

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4321. Min Act: -0.1700

Data Index: 1512449 (Python Code)

Max Activating Token Index: 333

Text #19

Max Range: 3.6670. Min Range: -3.6670

Max Act: 3.4321. Min Act: -0.1700

Data Index: 1611074 (Python Code)

Max Activating Token Index: 803