Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1781 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.8641. Min Act: -0.1700

Data Index: 1019718 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.8641. Min Act: -0.1700

Data Index: 853258 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.8641. Min Act: -0.1700

Data Index: 1155433 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.8328. Min Act: -0.1700

Data Index: 199317 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.8328. Min Act: -0.1700

Data Index: 952411 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.8015. Min Act: -0.1700

Data Index: 529211 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7390. Min Act: -0.1700

Data Index: 775685 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7702. Min Act: -0.1700

Data Index: 1009134 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7702. Min Act: -0.1700

Data Index: 7236 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7233. Min Act: -0.1700

Data Index: 65033 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7233. Min Act: -0.1700

Data Index: 10558 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7702. Min Act: -0.1700

Data Index: 1317015 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6920. Min Act: -0.1700

Data Index: 989649 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6920. Min Act: -0.1700

Data Index: 1024116 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6764. Min Act: -0.1700

Data Index: 356250 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.7077. Min Act: -0.1700

Data Index: 736909 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6920. Min Act: -0.1700

Data Index: 421236 (C4 (Web Text))

Max Activating Token Index: 170

Text #17

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6764. Min Act: -0.1700

Data Index: 720554 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6607. Min Act: -0.1700

Data Index: 801047 (C4 (Web Text))

Max Activating Token Index: 400

Text #19

Max Range: 3.8641. Min Range: -3.8641

Max Act: 3.6607. Min Act: -0.1700

Data Index: 1290725 (C4 (Web Text))

Max Activating Token Index: 432