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

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

Neuron 1912 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: 5.6903. Min Range: -5.6903

Max Act: 5.6903. Min Act: -0.1700

Data Index: 1343488 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.5966. Min Act: -0.1700

Data Index: 414340 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.3153. Min Act: -0.1700

Data Index: 1123559 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2528. Min Act: -0.1700

Data Index: 188157 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2216. Min Act: -0.1700

Data Index: 1003940 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2841. Min Act: -0.1700

Data Index: 689074 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2841. Min Act: -0.1700

Data Index: 649230 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2216. Min Act: -0.1700

Data Index: 842546 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2841. Min Act: -0.1700

Data Index: 442389 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.3153. Min Act: -0.1700

Data Index: 453281 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2216. Min Act: -0.1700

Data Index: 140346 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1903. Min Act: -0.1700

Data Index: 766728 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.2059. Min Act: -0.1700

Data Index: 547918 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1747. Min Act: -0.1700

Data Index: 524111 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1903. Min Act: -0.1700

Data Index: 1176170 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1903. Min Act: -0.1700

Data Index: 1062708 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1278. Min Act: -0.1700

Data Index: 1320351 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1591. Min Act: -0.1700

Data Index: 686343 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1903. Min Act: -0.1700

Data Index: 471039 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 5.6903. Min Range: -5.6903

Max Act: 5.1122. Min Act: -0.1700

Data Index: 619012 (C4 (Web Text))

Max Activating Token Index: 302