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

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

Neuron 1388 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: 3.6834. Min Range: -3.6834

Max Act: 3.6834. Min Act: -0.1700

Data Index: 669614 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5269. Min Act: -0.1700

Data Index: 80487 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.5112. Min Act: -0.1700

Data Index: 108422 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4955. Min Act: -0.1700

Data Index: 196521 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4642. Min Act: -0.1700

Data Index: 197384 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4172. Min Act: -0.1700

Data Index: 328774 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4172. Min Act: -0.1700

Data Index: 995428 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4172. Min Act: -0.1700

Data Index: 225438 (C4 (Web Text))

Max Activating Token Index: 487

Text #8

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4328. Min Act: -0.1700

Data Index: 1157104 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4328. Min Act: -0.1700

Data Index: 294217 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3858. Min Act: -0.1700

Data Index: 1016173 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4015. Min Act: -0.1700

Data Index: 49701 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4015. Min Act: -0.1700

Data Index: 101826 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3544. Min Act: -0.1700

Data Index: 342712 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3858. Min Act: -0.1700

Data Index: 784214 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3544. Min Act: -0.1700

Data Index: 1028058 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.4328. Min Act: -0.1700

Data Index: 75206 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3544. Min Act: -0.1700

Data Index: 805552 (C4 (Web Text))

Max Activating Token Index: 656

Text #18

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3544. Min Act: -0.1700

Data Index: 716295 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 3.6834. Min Range: -3.6834

Max Act: 3.3544. Min Act: -0.1700

Data Index: 745828 (C4 (Web Text))

Max Activating Token Index: 730