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

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

Neuron 18 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.7641. Min Act: -0.1700

Data Index: 688663 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.7328. Min Act: -0.1699

Data Index: 938423 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.7328. Min Act: -0.1700

Data Index: 408249 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.6389. Min Act: -0.1700

Data Index: 1168840 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.6076. Min Act: -0.1700

Data Index: 906687 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5450. Min Act: -0.1700

Data Index: 380324 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5136. Min Act: -0.1700

Data Index: 1292394 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5450. Min Act: -0.1700

Data Index: 376192 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1271548 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5763. Min Act: -0.1700

Data Index: 857983 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5136. Min Act: -0.1700

Data Index: 63960 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5136. Min Act: -0.1700

Data Index: 730514 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5136. Min Act: -0.1700

Data Index: 1013831 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5136. Min Act: -0.1700

Data Index: 1303298 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.4823. Min Act: -0.1700

Data Index: 889572 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.4823. Min Act: -0.1700

Data Index: 364542 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.4823. Min Act: -0.1700

Data Index: 267108 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.5136. Min Act: -0.1700

Data Index: 186052 (C4 (Web Text))

Max Activating Token Index: 98

Text #18

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.4823. Min Act: -0.1700

Data Index: 1238763 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 3.7641. Min Range: -3.7641

Max Act: 3.4823. Min Act: -0.1700

Data Index: 1126769 (C4 (Web Text))

Max Activating Token Index: 719