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

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

Neuron 595 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: 5.0329. Min Range: -5.0329

Max Act: 5.0329. Min Act: -0.1700

Data Index: 529396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.9704. Min Act: -0.1700

Data Index: 681565 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 710677 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.8141. Min Act: -0.1700

Data Index: 370838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7829. Min Act: -0.1700

Data Index: 565019 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 1324190 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7204. Min Act: -0.1700

Data Index: 1273254 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 886044 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 975365 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 995319 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 234690 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.6891. Min Act: -0.1700

Data Index: 381658 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7204. Min Act: -0.1700

Data Index: 1196107 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.6891. Min Act: -0.1700

Data Index: 576742 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.6579. Min Act: -0.1700

Data Index: 1065244 (C4 (Web Text))

Max Activating Token Index: 798

Text #15

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.6891. Min Act: -0.1700

Data Index: 1100264 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.6891. Min Act: -0.1700

Data Index: 464278 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.6579. Min Act: -0.1700

Data Index: 375772 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7204. Min Act: -0.1700

Data Index: 1110425 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 5.0329. Min Range: -5.0329

Max Act: 4.7516. Min Act: -0.1700

Data Index: 1193797 (C4 (Web Text))

Max Activating Token Index: 841