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

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

Neuron 1868 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: 7.1324. Min Range: -7.1324

Max Act: 7.1324. Min Act: -0.1700

Data Index: 821181 (C4 (Web Text))

Max Activating Token Index: 497

Text #1

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.9761. Min Act: -0.1700

Data Index: 229526 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.8199. Min Act: -0.1700

Data Index: 591194 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 7.1324. Min Range: -7.1324

Max Act: 7.0699. Min Act: -0.1700

Data Index: 498079 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.7886. Min Act: -0.1700

Data Index: 511342 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.9449. Min Act: -0.1700

Data Index: 1191328 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 7.1324. Min Range: -7.1324

Max Act: 7.0074. Min Act: -0.1700

Data Index: 1129035 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.9761. Min Act: -0.1700

Data Index: 506190 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.8199. Min Act: -0.1700

Data Index: 733119 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.8511. Min Act: -0.1700

Data Index: 106776 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.8824. Min Act: -0.1700

Data Index: 414918 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.9136. Min Act: -0.1700

Data Index: 600460 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.7886. Min Act: -0.1700

Data Index: 82118 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.6636. Min Act: -0.1700

Data Index: 1305727 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.6324. Min Act: -0.1700

Data Index: 892918 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.6324. Min Act: -0.1700

Data Index: 1113760 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.7261. Min Act: -0.1700

Data Index: 357655 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.6011. Min Act: -0.1700

Data Index: 299903 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.6324. Min Act: -0.1700

Data Index: 37628 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 7.1324. Min Range: -7.1324

Max Act: 6.5386. Min Act: -0.1700

Data Index: 17751 (C4 (Web Text))

Max Activating Token Index: 353