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

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

Neuron 1590 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: 3.8201. Min Range: -3.8201

Max Act: 3.8201. Min Act: -0.1700

Data Index: 1226757 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.8045. Min Act: -0.1700

Data Index: 82381 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.8201. Min Act: -0.1700

Data Index: 1027920 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7889. Min Act: -0.1700

Data Index: 420818 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7576. Min Act: -0.1700

Data Index: 1179881 (C4 (Web Text))

Max Activating Token Index: 13

Text #5

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7419. Min Act: -0.1700

Data Index: 538636 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7576. Min Act: -0.1700

Data Index: 527521 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7576. Min Act: -0.1700

Data Index: 196569 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7419. Min Act: -0.1700

Data Index: 59528 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7419. Min Act: -0.1700

Data Index: 532214 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7419. Min Act: -0.1700

Data Index: 576975 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7419. Min Act: -0.1700

Data Index: 50201 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7263. Min Act: -0.1700

Data Index: 1185738 (C4 (Web Text))

Max Activating Token Index: 957

Text #13

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7106. Min Act: -0.1700

Data Index: 637743 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7106. Min Act: -0.1700

Data Index: 1130024 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7263. Min Act: -0.1700

Data Index: 809773 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7106. Min Act: -0.1700

Data Index: 1134948 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7263. Min Act: -0.1700

Data Index: 474502 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7263. Min Act: -0.1700

Data Index: 496298 (C4 (Web Text))

Max Activating Token Index: 53

Text #19

Max Range: 3.8201. Min Range: -3.8201

Max Act: 3.7263. Min Act: -0.1700

Data Index: 1193419 (C4 (Web Text))

Max Activating Token Index: 26