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

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

Neuron 1379 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1176. Min Range: -3.1176

Max Act: 3.1176. Min Act: -0.1700

Data Index: 1182165 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9914. Min Act: -0.1700

Data Index: 1225644 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 3.1176. Min Range: -3.1176

Max Act: 3.0230. Min Act: -0.1700

Data Index: 535602 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 3.1176. Min Range: -3.1176

Max Act: 3.0388. Min Act: -0.1700

Data Index: 846012 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.1176. Min Range: -3.1176

Max Act: 3.0072. Min Act: -0.1700

Data Index: 1149910 (C4 (Web Text))

Max Activating Token Index: 943

Text #5

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9914. Min Act: -0.1700

Data Index: 1112774 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9914. Min Act: -0.1700

Data Index: 973349 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9597. Min Act: -0.1700

Data Index: 617518 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9914. Min Act: -0.1700

Data Index: 246411 (C4 (Web Text))

Max Activating Token Index: 6

Text #9

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9755. Min Act: -0.1700

Data Index: 1065206 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9914. Min Act: -0.1700

Data Index: 731515 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9755. Min Act: -0.1700

Data Index: 142616 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 3.1176. Min Range: -3.1176

Max Act: 3.0230. Min Act: -0.1700

Data Index: 851244 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9597. Min Act: -0.1700

Data Index: 732534 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9755. Min Act: -0.1700

Data Index: 1070289 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9439. Min Act: -0.1700

Data Index: 347885 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9439. Min Act: -0.1700

Data Index: 473768 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9597. Min Act: -0.1700

Data Index: 262861 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9597. Min Act: -0.1700

Data Index: 747015 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 3.1176. Min Range: -3.1176

Max Act: 2.9597. Min Act: -0.1700

Data Index: 697763 (C4 (Web Text))

Max Activating Token Index: 347