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

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

Neuron 1177 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0381. Min Range: -4.0381

Max Act: 4.0381. Min Act: -0.1700

Data Index: 635141 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.7879. Min Act: -0.1700

Data Index: 72593 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.8192. Min Act: -0.1700

Data Index: 78323 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.7566. Min Act: -0.1700

Data Index: 191759 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.7879. Min Act: -0.1700

Data Index: 224403 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.7879. Min Act: -0.1700

Data Index: 30898 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.8192. Min Act: -0.1700

Data Index: 156549 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.7566. Min Act: -0.1700

Data Index: 1092282 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.7254. Min Act: -0.1700

Data Index: 57712 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6941. Min Act: -0.1700

Data Index: 215749 (C4 (Web Text))

Max Activating Token Index: 577

Text #10

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6315. Min Act: -0.1700

Data Index: 587921 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6941. Min Act: -0.1700

Data Index: 1165822 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6315. Min Act: -0.1700

Data Index: 781314 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6315. Min Act: -0.1700

Data Index: 415024 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6315. Min Act: -0.1700

Data Index: 183966 (C4 (Web Text))

Max Activating Token Index: 241

Text #15

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6001. Min Act: -0.1699

Data Index: 783146 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6628. Min Act: -0.1700

Data Index: 451971 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6628. Min Act: -0.1700

Data Index: 843952 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.6001. Min Act: -0.1700

Data Index: 950453 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 4.0381. Min Range: -4.0381

Max Act: 3.5688. Min Act: -0.1700

Data Index: 379307 (C4 (Web Text))

Max Activating Token Index: 1023