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

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

Neuron 1094 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: 3.1279. Min Range: -3.1279

Max Act: 3.1279. Min Act: -0.1700

Data Index: 732508 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.1279. Min Range: -3.1279

Max Act: 3.0964. Min Act: -0.1700

Data Index: 1201582 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.1279. Min Range: -3.1279

Max Act: 3.0017. Min Act: -0.1700

Data Index: 345119 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.9858. Min Act: -0.1700

Data Index: 532227 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.9542. Min Act: -0.1700

Data Index: 1349639 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.8749. Min Act: -0.1700

Data Index: 1324453 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.9858. Min Act: -0.1700

Data Index: 1300139 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.9067. Min Act: -0.1700

Data Index: 832647 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.8590. Min Act: -0.1700

Data Index: 1245916 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.8113. Min Act: -0.1700

Data Index: 452933 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.8113. Min Act: -0.1700

Data Index: 1618133 (Python Code)

Max Activating Token Index: 746

Text #11

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7954. Min Act: -0.1700

Data Index: 325845 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7635. Min Act: -0.1700

Data Index: 617562 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7635. Min Act: -0.1700

Data Index: 515058 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7316. Min Act: -0.1700

Data Index: 751777 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7795. Min Act: -0.1700

Data Index: 114683 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.6676. Min Act: -0.1700

Data Index: 755588 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7476. Min Act: -0.1700

Data Index: 854785 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7476. Min Act: -0.1700

Data Index: 930411 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 3.1279. Min Range: -3.1279

Max Act: 2.7795. Min Act: -0.1700

Data Index: 1131809 (C4 (Web Text))

Max Activating Token Index: 1023