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

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

Neuron 632 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: 3.8335. Min Range: -3.8335

Max Act: 3.8335. Min Act: -0.1700

Data Index: 111607 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.8022. Min Act: -0.1700

Data Index: 631533 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7709. Min Act: -0.1699

Data Index: 1079976 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6771. Min Act: -0.1700

Data Index: 669787 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.7084. Min Act: -0.1700

Data Index: 1323848 (C4 (Web Text))

Max Activating Token Index: 741

Text #5

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1177230 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6458. Min Act: -0.1700

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6771. Min Act: -0.1700

Data Index: 584403 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6771. Min Act: -0.1700

Data Index: 66464 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1220139 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1067873 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6458. Min Act: -0.1700

Data Index: 397120 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6144. Min Act: -0.1700

Data Index: 798691 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6144. Min Act: -0.1700

Data Index: 1062353 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6144. Min Act: -0.1699

Data Index: 480411 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6458. Min Act: -0.1700

Data Index: 704975 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6144. Min Act: -0.1700

Data Index: 670166 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6144. Min Act: -0.1700

Data Index: 196723 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.5831. Min Act: -0.1700

Data Index: 785065 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 3.8335. Min Range: -3.8335

Max Act: 3.6144. Min Act: -0.1700

Data Index: 639352 (C4 (Web Text))

Max Activating Token Index: 394