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

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

Neuron 948 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: 8.1024. Min Range: -8.1024

Max Act: 8.0399. Min Act: -0.1700

Data Index: 1331672 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 8.1024. Min Range: -8.1024

Max Act: 8.1024. Min Act: -0.1700

Data Index: 568953 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 8.1024. Min Range: -8.1024

Max Act: 8.0399. Min Act: -0.1700

Data Index: 579855 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.9774. Min Act: -0.1700

Data Index: 559710 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.9149. Min Act: -0.1699

Data Index: 905785 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.9149. Min Act: -0.1700

Data Index: 1261893 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.7899. Min Act: -0.1700

Data Index: 297705 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.7899. Min Act: -0.1700

Data Index: 372966 (C4 (Web Text))

Max Activating Token Index: 484

Text #8

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.7274. Min Act: -0.1700

Data Index: 262086 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.7274. Min Act: -0.1700

Data Index: 344892 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.6961. Min Act: -0.1700

Data Index: 741132 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.6336. Min Act: -0.1700

Data Index: 1124534 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.6961. Min Act: -0.1700

Data Index: 1159961 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.5399. Min Act: -0.1700

Data Index: 1225017 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.6024. Min Act: -0.1700

Data Index: 31294 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.6024. Min Act: -0.1700

Data Index: 1121166 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.6336. Min Act: -0.1700

Data Index: 763206 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.5399. Min Act: -0.1700

Data Index: 245008 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.5399. Min Act: -0.1700

Data Index: 584399 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 8.1024. Min Range: -8.1024

Max Act: 7.5399. Min Act: -0.1700

Data Index: 394203 (C4 (Web Text))

Max Activating Token Index: 885