Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1374 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.4419. Min Act: -0.1700

Data Index: 159304 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3478. Min Act: -0.1700

Data Index: 820752 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1288470 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3478. Min Act: -0.1700

Data Index: 616490 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3791. Min Act: -0.1700

Data Index: 1025116 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3478. Min Act: -0.1700

Data Index: 280261 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3164. Min Act: -0.1700

Data Index: 339605 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.3164. Min Act: -0.1700

Data Index: 480295 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2849. Min Act: -0.1700

Data Index: 740267 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2535. Min Act: -0.1700

Data Index: 862110 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2535. Min Act: -0.1700

Data Index: 1657030 (Python Code)

Max Activating Token Index: 183

Text #11

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2535. Min Act: -0.1700

Data Index: 1374038 (Python Code)

Max Activating Token Index: 806

Text #12

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.1906. Min Act: -0.1700

Data Index: 492974 (C4 (Web Text))

Max Activating Token Index: 749

Text #13

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2849. Min Act: -0.1700

Data Index: 364235 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2221. Min Act: -0.1700

Data Index: 482261 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2221. Min Act: -0.1700

Data Index: 1023788 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2221. Min Act: -0.1700

Data Index: 972623 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.1906. Min Act: -0.1700

Data Index: 463688 (C4 (Web Text))

Max Activating Token Index: 759

Text #18

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.2535. Min Act: -0.1700

Data Index: 509726 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.4419. Min Range: -3.4419

Max Act: 3.1906. Min Act: -0.1700

Data Index: 48794 (C4 (Web Text))

Max Activating Token Index: 84