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

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

Neuron 1203 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.1292. Min Act: -0.1700

Data Index: 504464 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.2230. Min Act: -0.1700

Data Index: 1216575 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.1292. Min Act: -0.1700

Data Index: 233076 (C4 (Web Text))

Max Activating Token Index: 467

Text #3

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.1292. Min Act: -0.1700

Data Index: 1312541 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.1292. Min Act: -0.1700

Data Index: 84193 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0355. Min Act: -0.1700

Data Index: 327869 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.1917. Min Act: -0.1700

Data Index: 1300670 (C4 (Web Text))

Max Activating Token Index: 828

Text #7

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0980. Min Act: -0.1700

Data Index: 374289 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0667. Min Act: -0.1700

Data Index: 272859 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0667. Min Act: -0.1700

Data Index: 1332992 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0980. Min Act: -0.1700

Data Index: 1010693 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 7.2230. Min Range: -7.2230

Max Act: 6.9730. Min Act: -0.1700

Data Index: 270639 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0042. Min Act: -0.1700

Data Index: 1342682 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0042. Min Act: -0.1700

Data Index: 192700 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 7.2230. Min Range: -7.2230

Max Act: 6.9417. Min Act: -0.1700

Data Index: 771045 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0042. Min Act: -0.1700

Data Index: 581007 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 7.2230. Min Range: -7.2230

Max Act: 6.8792. Min Act: -0.1700

Data Index: 1004306 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0042. Min Act: -0.1700

Data Index: 1064809 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 7.2230. Min Range: -7.2230

Max Act: 7.0042. Min Act: -0.1700

Data Index: 500163 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 7.2230. Min Range: -7.2230

Max Act: 6.9417. Min Act: -0.1700

Data Index: 80300 (C4 (Web Text))

Max Activating Token Index: 27