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

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

Neuron 1089 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: 5.8924. Min Range: -5.8924

Max Act: 5.8924. Min Act: -0.1700

Data Index: 491672 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.8299. Min Act: -0.1700

Data Index: 1000093 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7986. Min Act: -0.1700

Data Index: 1020962 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.8299. Min Act: -0.1700

Data Index: 126394 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.8299. Min Act: -0.1700

Data Index: 663534 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.8299. Min Act: -0.1700

Data Index: 254587 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7674. Min Act: -0.1700

Data Index: 118698 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7674. Min Act: -0.1700

Data Index: 156514 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7361. Min Act: -0.1700

Data Index: 1054818 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7361. Min Act: -0.1700

Data Index: 716670 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7361. Min Act: -0.1700

Data Index: 729845 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.8299. Min Act: -0.1700

Data Index: 1108044 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7674. Min Act: -0.1700

Data Index: 155627 (C4 (Web Text))

Max Activating Token Index: 517

Text #13

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7361. Min Act: -0.1700

Data Index: 429238 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7674. Min Act: -0.1700

Data Index: 432269 (C4 (Web Text))

Max Activating Token Index: 740

Text #15

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7986. Min Act: -0.1700

Data Index: 711255 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7049. Min Act: -0.1700

Data Index: 1046988 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7674. Min Act: -0.1700

Data Index: 132784 (C4 (Web Text))

Max Activating Token Index: 831

Text #18

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7361. Min Act: -0.1700

Data Index: 731351 (C4 (Web Text))

Max Activating Token Index: 519

Text #19

Max Range: 5.8924. Min Range: -5.8924

Max Act: 5.7361. Min Act: -0.1700

Data Index: 944405 (C4 (Web Text))

Max Activating Token Index: 888