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

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

Neuron 17 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: 3.8213. Min Range: -3.8213

Max Act: 3.8213. Min Act: -0.1700

Data Index: 596837 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6805. Min Act: -0.1700

Data Index: 1268500 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6805. Min Act: -0.1700

Data Index: 1252742 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6335. Min Act: -0.1700

Data Index: 134554 (C4 (Web Text))

Max Activating Token Index: 870

Text #4

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6179. Min Act: -0.1700

Data Index: 660620 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 1307857 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6179. Min Act: -0.1700

Data Index: 52582 (C4 (Web Text))

Max Activating Token Index: 996

Text #7

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 300645 (C4 (Web Text))

Max Activating Token Index: 562

Text #8

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 920948 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5709. Min Act: -0.1700

Data Index: 1114096 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.6022. Min Act: -0.1700

Data Index: 1135191 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 678651 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 1043043 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5866. Min Act: -0.1700

Data Index: 177694 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5552. Min Act: -0.1700

Data Index: 800033 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5709. Min Act: -0.1700

Data Index: 1284446 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5396. Min Act: -0.1700

Data Index: 563916 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5239. Min Act: -0.1700

Data Index: 381626 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5239. Min Act: -0.1700

Data Index: 683494 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 3.8213. Min Range: -3.8213

Max Act: 3.5396. Min Act: -0.1700

Data Index: 637635 (C4 (Web Text))

Max Activating Token Index: 761