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

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

Neuron 827 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: 5.2797. Min Range: -5.2797

Max Act: 5.2485. Min Act: -0.1700

Data Index: 404694 (C4 (Web Text))

Max Activating Token Index: 850

Text #1

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.2797. Min Act: -0.1700

Data Index: 1272632 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.2797. Min Act: -0.1700

Data Index: 984586 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.2485. Min Act: -0.1700

Data Index: 871186 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.2797. Min Act: -0.1700

Data Index: 1349565 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.1235. Min Act: -0.1700

Data Index: 220733 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.1547. Min Act: -0.1700

Data Index: 680186 (C4 (Web Text))

Max Activating Token Index: 295

Text #7

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.1547. Min Act: -0.1700

Data Index: 635147 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.1547. Min Act: -0.1700

Data Index: 1079780 (C4 (Web Text))

Max Activating Token Index: 810

Text #9

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0922. Min Act: -0.1700

Data Index: 1064416 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0922. Min Act: -0.1700

Data Index: 875292 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0610. Min Act: -0.1700

Data Index: 228337 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.1235. Min Act: -0.1700

Data Index: 101968 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0922. Min Act: -0.1700

Data Index: 667841 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0922. Min Act: -0.1700

Data Index: 182169 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 5.2797. Min Range: -5.2797

Max Act: 4.9985. Min Act: -0.1700

Data Index: 65686 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0610. Min Act: -0.1700

Data Index: 511316 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0297. Min Act: -0.1700

Data Index: 1019490 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0610. Min Act: -0.1700

Data Index: 137738 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 5.2797. Min Range: -5.2797

Max Act: 5.0610. Min Act: -0.1700

Data Index: 423096 (C4 (Web Text))

Max Activating Token Index: 120