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

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

Neuron 1884 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.3003. Min Act: -0.1700

Data Index: 697212 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2846. Min Act: -0.1700

Data Index: 280840 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2689. Min Act: -0.1700

Data Index: 359922 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2532. Min Act: -0.1700

Data Index: 686244 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2689. Min Act: -0.1700

Data Index: 121305 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2217. Min Act: -0.1700

Data Index: 166280 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2375. Min Act: -0.1700

Data Index: 583855 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2217. Min Act: -0.1700

Data Index: 186609 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1903. Min Act: -0.1700

Data Index: 485904 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2375. Min Act: -0.1700

Data Index: 1250320 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1903. Min Act: -0.1700

Data Index: 472071 (C4 (Web Text))

Max Activating Token Index: 712

Text #11

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1903. Min Act: -0.1700

Data Index: 817299 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1745. Min Act: -0.1700

Data Index: 689348 (C4 (Web Text))

Max Activating Token Index: 356

Text #13

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1903. Min Act: -0.1700

Data Index: 32467 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1588. Min Act: -0.1700

Data Index: 1210499 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.2060. Min Act: -0.1700

Data Index: 815938 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1903. Min Act: -0.1700

Data Index: 312436 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1588. Min Act: -0.1700

Data Index: 980310 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1745. Min Act: -0.1700

Data Index: 1006538 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 3.3003. Min Range: -3.3003

Max Act: 3.1588. Min Act: -0.1700

Data Index: 129527 (C4 (Web Text))

Max Activating Token Index: 767