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

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

Neuron 1728 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: 5.7419. Min Range: -5.7419

Max Act: 5.7419. Min Act: -0.1700

Data Index: 325939 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.7419. Min Act: -0.1700

Data Index: 1267992 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.6794. Min Act: -0.1700

Data Index: 388681 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.7107. Min Act: -0.1700

Data Index: 851162 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.6794. Min Act: -0.1700

Data Index: 200145 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.5857. Min Act: -0.1700

Data Index: 43933 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.5544. Min Act: -0.1700

Data Index: 774009 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.5232. Min Act: -0.1700

Data Index: 391280 (C4 (Web Text))

Max Activating Token Index: 328

Text #8

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.4607. Min Act: -0.1700

Data Index: 960828 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3982. Min Act: -0.1700

Data Index: 154305 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.4294. Min Act: -0.1700

Data Index: 314864 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.4607. Min Act: -0.1700

Data Index: 726955 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3982. Min Act: -0.1700

Data Index: 582429 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3982. Min Act: -0.1700

Data Index: 943402 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3669. Min Act: -0.1700

Data Index: 374675 (C4 (Web Text))

Max Activating Token Index: 744

Text #15

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3357. Min Act: -0.1700

Data Index: 186676 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3357. Min Act: -0.1700

Data Index: 1298700 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3669. Min Act: -0.1700

Data Index: 58468 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3669. Min Act: -0.1700

Data Index: 193852 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 5.7419. Min Range: -5.7419

Max Act: 5.3669. Min Act: -0.1700

Data Index: 406799 (C4 (Web Text))

Max Activating Token Index: 553