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

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

Neuron 706 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: 3.9930. Min Range: -3.9930

Max Act: 3.9930. Min Act: -0.1700

Data Index: 552063 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.9304. Min Act: -0.1700

Data Index: 81595 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.9304. Min Act: -0.1700

Data Index: 781457 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8992. Min Act: -0.1700

Data Index: 961994 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8366. Min Act: -0.1700

Data Index: 220250 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8992. Min Act: -0.1700

Data Index: 463476 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8992. Min Act: -0.1700

Data Index: 1279749 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8992. Min Act: -0.1700

Data Index: 377362 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8679. Min Act: -0.1700

Data Index: 908387 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8679. Min Act: -0.1700

Data Index: 194095 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8679. Min Act: -0.1700

Data Index: 541706 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8053. Min Act: -0.1700

Data Index: 873255 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8679. Min Act: -0.1700

Data Index: 853468 (C4 (Web Text))

Max Activating Token Index: 542

Text #13

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8679. Min Act: -0.1700

Data Index: 1089067 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8366. Min Act: -0.1700

Data Index: 660227 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8053. Min Act: -0.1700

Data Index: 350758 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8053. Min Act: -0.1700

Data Index: 437194 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8053. Min Act: -0.1700

Data Index: 321947 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8053. Min Act: -0.1700

Data Index: 822305 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 3.9930. Min Range: -3.9930

Max Act: 3.8679. Min Act: -0.1700

Data Index: 828787 (C4 (Web Text))

Max Activating Token Index: 675