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

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

Neuron 1404 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: 5.3511. Min Range: -5.3511

Max Act: 5.3511. Min Act: -0.1700

Data Index: 324364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.3199. Min Act: -0.1700

Data Index: 204745 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.2261. Min Act: -0.1700

Data Index: 1305116 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.1324. Min Act: -0.1700

Data Index: 1138214 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.1011. Min Act: -0.1700

Data Index: 1084517 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.0699. Min Act: -0.1700

Data Index: 71080 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.0386. Min Act: -0.1699

Data Index: 675502 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.0074. Min Act: -0.1700

Data Index: 586302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 5.3511. Min Range: -5.3511

Max Act: 5.0386. Min Act: -0.1700

Data Index: 499719 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9761. Min Act: -0.1700

Data Index: 620946 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9761. Min Act: -0.1700

Data Index: 789420 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9761. Min Act: -0.1700

Data Index: 91949 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9761. Min Act: -0.1700

Data Index: 30668 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9761. Min Act: -0.1700

Data Index: 781591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9449. Min Act: -0.1700

Data Index: 402071 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9449. Min Act: -0.1700

Data Index: 967592 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9136. Min Act: -0.1700

Data Index: 239424 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.8824. Min Act: -0.1700

Data Index: 1092004 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9136. Min Act: -0.1700

Data Index: 1203830 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 5.3511. Min Range: -5.3511

Max Act: 4.9449. Min Act: -0.1700

Data Index: 1219484 (C4 (Web Text))

Max Activating Token Index: 1023