Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1234 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9566. Min Act: -0.1700

Data Index: 1275946 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9340. Min Act: -0.1700

Data Index: 192543 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9057. Min Act: -0.1700

Data Index: 690145 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9160. Min Act: -0.1700

Data Index: 333784 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9120. Min Act: -0.1700

Data Index: 1357417 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9150. Min Act: -0.1700

Data Index: 743715 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8852. Min Act: -0.1700

Data Index: 1006765 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8501. Min Act: -0.1700

Data Index: 759579 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.9017. Min Act: -0.1700

Data Index: 867264 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8678. Min Act: -0.1700

Data Index: 544730 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8436. Min Act: -0.1700

Data Index: 63098 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8373. Min Act: -0.1700

Data Index: 5812 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8252. Min Act: -0.1700

Data Index: 1328628 (C4 (Web Text))

Max Activating Token Index: 256

Text #13

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8382. Min Act: -0.1700

Data Index: 218676 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8169. Min Act: -0.1700

Data Index: 388457 (C4 (Web Text))

Max Activating Token Index: 170

Text #15

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.7812. Min Act: -0.1700

Data Index: 1639549 (Python Code)

Max Activating Token Index: 950

Text #16

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8018. Min Act: -0.1700

Data Index: 698363 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8058. Min Act: -0.1700

Data Index: 601099 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8185. Min Act: -0.1700

Data Index: 690087 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 2.9566. Min Range: -2.9566

Max Act: 2.8159. Min Act: -0.1700

Data Index: 251088 (C4 (Web Text))

Max Activating Token Index: 366