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

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

Neuron 433 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.3419. Min Act: -0.1700

Data Index: 714304 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.3262. Min Act: -0.1700

Data Index: 1167705 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.3262. Min Act: -0.1700

Data Index: 963305 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.2634. Min Act: -0.1700

Data Index: 703560 (C4 (Web Text))

Max Activating Token Index: 449

Text #4

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.2477. Min Act: -0.1700

Data Index: 408679 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.2477. Min Act: -0.1700

Data Index: 1253791 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.2162. Min Act: -0.1700

Data Index: 652477 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1847. Min Act: -0.1700

Data Index: 370903 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.2005. Min Act: -0.1700

Data Index: 119516 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1690. Min Act: -0.1700

Data Index: 699727 (C4 (Web Text))

Max Activating Token Index: 513

Text #10

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1690. Min Act: -0.1700

Data Index: 940221 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1375. Min Act: -0.1700

Data Index: 538795 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1375. Min Act: -0.1700

Data Index: 249348 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1533. Min Act: -0.1700

Data Index: 1039899 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1217. Min Act: -0.1700

Data Index: 28399 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1217. Min Act: -0.1700

Data Index: 799729 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1217. Min Act: -0.1700

Data Index: 125027 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1375. Min Act: -0.1700

Data Index: 92297 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1217. Min Act: -0.1700

Data Index: 615541 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 3.3419. Min Range: -3.3419

Max Act: 3.1375. Min Act: -0.1700

Data Index: 502796 (C4 (Web Text))

Max Activating Token Index: 702