Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 715 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.9398. Min Act: -0.1700

Data Index: 608457 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.9202. Min Act: -0.1700

Data Index: 688752 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.8103. Min Act: -0.1700

Data Index: 269453 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.7078. Min Act: -0.1700

Data Index: 1186650 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.6935. Min Act: -0.1700

Data Index: 35356 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.6686. Min Act: -0.1700

Data Index: 205586 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.6784. Min Act: -0.1700

Data Index: 734130 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5901. Min Act: -0.1700

Data Index: 361046 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5989. Min Act: -0.1700

Data Index: 1241253 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5441. Min Act: -0.1700

Data Index: 357980 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5867. Min Act: -0.1700

Data Index: 303383 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5068. Min Act: -0.1700

Data Index: 1167026 (C4 (Web Text))

Max Activating Token Index: 832

Text #12

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.4957. Min Act: -0.1700

Data Index: 877230 (C4 (Web Text))

Max Activating Token Index: 197

Text #13

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5128. Min Act: -0.1700

Data Index: 106659 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.4805. Min Act: -0.1700

Data Index: 391512 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.5011. Min Act: -0.1700

Data Index: 1338565 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.4679. Min Act: -0.1700

Data Index: 1071531 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.4959. Min Act: -0.1700

Data Index: 1035272 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.4683. Min Act: -0.1700

Data Index: 904632 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 3.9398. Min Range: -3.9398

Max Act: 3.4675. Min Act: -0.1700

Data Index: 942816 (C4 (Web Text))

Max Activating Token Index: 901