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

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

Neuron 270 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: 3.5613. Min Range: -3.5613

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1300029 (C4 (Web Text))

Max Activating Token Index: 2

Text #1

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.5613. Min Act: -0.1700

Data Index: 775776 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4516. Min Act: -0.1700

Data Index: 1006269 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4516. Min Act: -0.1700

Data Index: 959179 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4516. Min Act: -0.1700

Data Index: 1248873 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4516. Min Act: -0.1700

Data Index: 879964 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4359. Min Act: -0.1700

Data Index: 1192318 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4359. Min Act: -0.1700

Data Index: 777855 (C4 (Web Text))

Max Activating Token Index: 873

Text #8

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4203. Min Act: -0.1700

Data Index: 224336 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1098449 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4359. Min Act: -0.1700

Data Index: 396271 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4203. Min Act: -0.1700

Data Index: 983280 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3889. Min Act: -0.1700

Data Index: 1388575 (Python Code)

Max Activating Token Index: 257

Text #13

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4046. Min Act: -0.1700

Data Index: 1177897 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3889. Min Act: -0.1700

Data Index: 801040 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.4046. Min Act: -0.1700

Data Index: 325520 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3889. Min Act: -0.1700

Data Index: 935598 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3732. Min Act: -0.1700

Data Index: 945310 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3889. Min Act: -0.1700

Data Index: 620488 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 3.5613. Min Range: -3.5613

Max Act: 3.3889. Min Act: -0.1700

Data Index: 622021 (C4 (Web Text))

Max Activating Token Index: 783