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

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

Neuron 1348 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: 3.4321. Min Range: -3.4321

Max Act: 3.4321. Min Act: -0.1700

Data Index: 245229 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.4321. Min Act: -0.1700

Data Index: 861246 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.4007. Min Act: -0.1700

Data Index: 1270656 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.4321. Min Act: -0.1700

Data Index: 852238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.4007. Min Act: -0.1700

Data Index: 1075346 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.4321. Min Act: -0.1700

Data Index: 855360 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3379. Min Act: -0.1700

Data Index: 225232 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3065. Min Act: -0.1700

Data Index: 32173 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3065. Min Act: -0.1700

Data Index: 986901 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3379. Min Act: -0.1700

Data Index: 407104 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3379. Min Act: -0.1700

Data Index: 188308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3379. Min Act: -0.1700

Data Index: 845204 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3065. Min Act: -0.1700

Data Index: 401099 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3065. Min Act: -0.1700

Data Index: 883154 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.3379. Min Act: -0.1700

Data Index: 749181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1582379 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2751. Min Act: -0.1700

Data Index: 1393590 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2751. Min Act: -0.1700

Data Index: 977766 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2751. Min Act: -0.1700

Data Index: 551199 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 3.4321. Min Range: -3.4321

Max Act: 3.2751. Min Act: -0.1700

Data Index: 715349 (C4 (Web Text))

Max Activating Token Index: 1023