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

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

Neuron 1223 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: 3.6684. Min Range: -3.6684

Max Act: 3.6684. Min Act: -0.1700

Data Index: 1179306 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6527. Min Act: -0.1700

Data Index: 887272 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6058. Min Act: -0.1700

Data Index: 1135721 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.6058. Min Act: -0.1700

Data Index: 1332397 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5745. Min Act: -0.1700

Data Index: 292204 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5745. Min Act: -0.1700

Data Index: 942 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5588. Min Act: -0.1700

Data Index: 1208893 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5431. Min Act: -0.1700

Data Index: 485571 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5431. Min Act: -0.1700

Data Index: 778054 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5275. Min Act: -0.1700

Data Index: 201587 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5275. Min Act: -0.1700

Data Index: 756326 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5118. Min Act: -0.1700

Data Index: 907920 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5275. Min Act: -0.1700

Data Index: 639499 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5275. Min Act: -0.1700

Data Index: 1009909 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5431. Min Act: -0.1700

Data Index: 435443 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5275. Min Act: -0.1700

Data Index: 779559 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5118. Min Act: -0.1700

Data Index: 88141 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5118. Min Act: -0.1700

Data Index: 229631 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.5118. Min Act: -0.1700

Data Index: 513434 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 3.6684. Min Range: -3.6684

Max Act: 3.4961. Min Act: -0.1700

Data Index: 905881 (C4 (Web Text))

Max Activating Token Index: 986