Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 773 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0274. Min Range: -4.0274

Max Act: 4.0274. Min Act: -0.1700

Data Index: 558730 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 4.0274. Min Range: -4.0274

Max Act: 4.0274. Min Act: -0.1700

Data Index: 981171 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.9336. Min Act: -0.1700

Data Index: 268854 (C4 (Web Text))

Max Activating Token Index: 549

Text #3

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.9493. Min Act: -0.1700

Data Index: 318396 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.8867. Min Act: -0.1700

Data Index: 1225130 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.8867. Min Act: -0.1700

Data Index: 656808 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.8711. Min Act: -0.1700

Data Index: 419640 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7929. Min Act: -0.1700

Data Index: 36882 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7929. Min Act: -0.1700

Data Index: 122252 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.8085. Min Act: -0.1700

Data Index: 753134 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7929. Min Act: -0.1700

Data Index: 902679 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7772. Min Act: -0.1700

Data Index: 893947 (C4 (Web Text))

Max Activating Token Index: 398

Text #12

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7616. Min Act: -0.1700

Data Index: 1179805 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7616. Min Act: -0.1700

Data Index: 957015 (C4 (Web Text))

Max Activating Token Index: 170

Text #14

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7616. Min Act: -0.1700

Data Index: 51476 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7772. Min Act: -0.1700

Data Index: 84820 (C4 (Web Text))

Max Activating Token Index: 445

Text #16

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7147. Min Act: -0.1700

Data Index: 455798 (C4 (Web Text))

Max Activating Token Index: 828

Text #17

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7459. Min Act: -0.1700

Data Index: 248388 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7303. Min Act: -0.1700

Data Index: 1045543 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 4.0274. Min Range: -4.0274

Max Act: 3.7459. Min Act: -0.1700

Data Index: 1136671 (C4 (Web Text))

Max Activating Token Index: 184