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

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

Neuron 1251 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: 3.1946. Min Range: -3.1946

Max Act: 3.1946. Min Act: -0.1644

Data Index: 1641491 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.9713. Min Act: -0.1700

Data Index: 1421261 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8950. Min Act: -0.1699

Data Index: 1487098 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8968. Min Act: -0.1700

Data Index: 1622161 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8929. Min Act: -0.1696

Data Index: 1499880 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8734. Min Act: -0.1700

Data Index: 1525488 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8686. Min Act: -0.1696

Data Index: 1494759 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8472. Min Act: -0.1699

Data Index: 1479905 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8290. Min Act: -0.1700

Data Index: 25103 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8410. Min Act: -0.1700

Data Index: 1046515 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8181. Min Act: -0.1700

Data Index: 164496 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8211. Min Act: -0.1695

Data Index: 1550834 (Python Code)

Max Activating Token Index: 948

Text #12

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8079. Min Act: -0.1699

Data Index: 1549520 (Python Code)

Max Activating Token Index: 311

Text #13

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.8000. Min Act: -0.1699

Data Index: 1531181 (Python Code)

Max Activating Token Index: 642

Text #14

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.7572. Min Act: -0.1698

Data Index: 1505204 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.7539. Min Act: -0.1699

Data Index: 1648616 (Python Code)

Max Activating Token Index: 352

Text #16

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.7606. Min Act: -0.1700

Data Index: 1154607 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.7061. Min Act: -0.1700

Data Index: 625350 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.6953. Min Act: -0.1700

Data Index: 1588852 (Python Code)

Max Activating Token Index: 1018

Text #19

Max Range: 3.1946. Min Range: -3.1946

Max Act: 2.7010. Min Act: -0.1700

Data Index: 1532383 (Python Code)

Max Activating Token Index: 1023