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

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

Neuron 420 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: 3.5750. Min Range: -3.5750

Max Act: 3.5750. Min Act: -0.1700

Data Index: 632680 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4810. Min Act: -0.1700

Data Index: 1180551 (C4 (Web Text))

Max Activating Token Index: 391

Text #2

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4497. Min Act: -0.1700

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4810. Min Act: -0.1700

Data Index: 176384 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4497. Min Act: -0.1700

Data Index: 1194306 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4810. Min Act: -0.1700

Data Index: 680461 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4497. Min Act: -0.1700

Data Index: 1060078 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4810. Min Act: -0.1700

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4183. Min Act: -0.1700

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4183. Min Act: -0.1700

Data Index: 1262023 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.4183. Min Act: -0.1700

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3870. Min Act: -0.1700

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3556. Min Act: -0.1700

Data Index: 1241546 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3242. Min Act: -0.1700

Data Index: 455310 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3242. Min Act: -0.1700

Data Index: 40514 (C4 (Web Text))

Max Activating Token Index: 804

Text #15

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3556. Min Act: -0.1700

Data Index: 332169 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3870. Min Act: -0.1700

Data Index: 312355 (C4 (Web Text))

Max Activating Token Index: 428

Text #17

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3556. Min Act: -0.1700

Data Index: 181225 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.3242. Min Act: -0.1700

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 3.5750. Min Range: -3.5750

Max Act: 3.2928. Min Act: -0.1700

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 173