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

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

Neuron 1486 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.7984. Min Act: -0.1700

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.7202. Min Act: -0.1700

Data Index: 334041 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.7045. Min Act: -0.1700

Data Index: 290481 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6419. Min Act: -0.1700

Data Index: 395353 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6732. Min Act: -0.1700

Data Index: 803360 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6419. Min Act: -0.1700

Data Index: 103094 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6263. Min Act: -0.1700

Data Index: 1305809 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6106. Min Act: -0.1700

Data Index: 207041 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6263. Min Act: -0.1700

Data Index: 240779 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.6106. Min Act: -0.1700

Data Index: 1317008 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5950. Min Act: -0.1700

Data Index: 1319583 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5950. Min Act: -0.1700

Data Index: 622246 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5793. Min Act: -0.1700

Data Index: 291168 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1096660 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5950. Min Act: -0.1700

Data Index: 954822 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5480. Min Act: -0.1700

Data Index: 231748 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5637. Min Act: -0.1700

Data Index: 388808 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5793. Min Act: -0.1700

Data Index: 1032933 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.5637. Min Act: -0.1700

Data Index: 1156664 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 3.7984. Min Range: -3.7984

Max Act: 3.4853. Min Act: -0.1700

Data Index: 1189929 (C4 (Web Text))

Max Activating Token Index: 524