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

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

Neuron 246 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: 4.1010. Min Range: -4.1010

Max Act: 4.1010. Min Act: -0.1700

Data Index: 281554 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 4.1010. Min Range: -4.1010

Max Act: 4.0385. Min Act: -0.1699

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.9916. Min Act: -0.1700

Data Index: 424903 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.9916. Min Act: -0.1700

Data Index: 203097 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.9290. Min Act: -0.1700

Data Index: 540609 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.9134. Min Act: -0.1700

Data Index: 615073 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8821. Min Act: -0.1700

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 374

Text #7

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.7726. Min Act: -0.1700

Data Index: 766101 (C4 (Web Text))

Max Activating Token Index: 745

Text #8

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8821. Min Act: -0.1700

Data Index: 1028144 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8665. Min Act: -0.1699

Data Index: 877443 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8352. Min Act: -0.1700

Data Index: 1019135 (C4 (Web Text))

Max Activating Token Index: 1002

Text #11

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8352. Min Act: -0.1700

Data Index: 474380 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.7101. Min Act: -0.1699

Data Index: 21010 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8665. Min Act: -0.1700

Data Index: 660730 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8508. Min Act: -0.1700

Data Index: 510681 (C4 (Web Text))

Max Activating Token Index: 769

Text #15

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8196. Min Act: -0.1700

Data Index: 579092 (C4 (Web Text))

Max Activating Token Index: 991

Text #16

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8508. Min Act: -0.1700

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.7257. Min Act: -0.1700

Data Index: 382590 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8196. Min Act: -0.1700

Data Index: 1035890 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 4.1010. Min Range: -4.1010

Max Act: 3.8196. Min Act: -0.1700

Data Index: 106121 (C4 (Web Text))

Max Activating Token Index: 698