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

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

Neuron 614 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: 3.2576. Min Range: -3.2576

Max Act: 3.2576. Min Act: -0.1699

Data Index: 1409489 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.9915. Min Act: -0.1700

Data Index: 1488531 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.9725. Min Act: -0.1700

Data Index: 1309955 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.9476. Min Act: -0.1700

Data Index: 1428085 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.9282. Min Act: -0.1700

Data Index: 1463814 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8604. Min Act: -0.1700

Data Index: 1457911 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8623. Min Act: -0.1700

Data Index: 1534967 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8627. Min Act: -0.1697

Data Index: 1592871 (Python Code)

Max Activating Token Index: 236

Text #8

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8437. Min Act: -0.1700

Data Index: 1471547 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8175. Min Act: -0.1700

Data Index: 1651791 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8018. Min Act: -0.1700

Data Index: 1490508 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7849. Min Act: -0.1700

Data Index: 1586344 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7993. Min Act: -0.1700

Data Index: 1491814 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8015. Min Act: -0.1700

Data Index: 1546786 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7904. Min Act: -0.1700

Data Index: 1613930 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8004. Min Act: -0.1700

Data Index: 1585179 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7952. Min Act: -0.1700

Data Index: 1585461 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.8031. Min Act: -0.1700

Data Index: 200159 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7830. Min Act: -0.1700

Data Index: 1422864 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.2576. Min Range: -3.2576

Max Act: 2.7699. Min Act: -0.1700

Data Index: 1571457 (Python Code)

Max Activating Token Index: 1023