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

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

Neuron 634 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.8753. Min Act: -0.1700

Data Index: 794753 (C4 (Web Text))

Max Activating Token Index: 119

Text #1

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.6566. Min Act: -0.1700

Data Index: 274322 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.5628. Min Act: -0.1700

Data Index: 1182037 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.6253. Min Act: -0.1700

Data Index: 1220249 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4378. Min Act: -0.1700

Data Index: 234328 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.5316. Min Act: -0.1700

Data Index: 1328446 (C4 (Web Text))

Max Activating Token Index: 655

Text #6

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4378. Min Act: -0.1699

Data Index: 817121 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4066. Min Act: -0.1700

Data Index: 241634 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4066. Min Act: -0.1700

Data Index: 814072 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4378. Min Act: -0.1700

Data Index: 909548 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4066. Min Act: -0.1699

Data Index: 820668 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.3753. Min Act: -0.1700

Data Index: 583093 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.4066. Min Act: -0.1700

Data Index: 840220 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.3441. Min Act: -0.1700

Data Index: 1320101 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.3441. Min Act: -0.1700

Data Index: 1106720 (C4 (Web Text))

Max Activating Token Index: 67

Text #15

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.3441. Min Act: -0.1700

Data Index: 198613 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.2816. Min Act: -0.1700

Data Index: 370922 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.3128. Min Act: -0.1700

Data Index: 5754 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.3128. Min Act: -0.1700

Data Index: 1289885 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 5.8753. Min Range: -5.8753

Max Act: 5.2816. Min Act: -0.1700

Data Index: 724915 (C4 (Web Text))

Max Activating Token Index: 352