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

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

Neuron 935 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: 5.9079. Min Range: -5.9079

Max Act: 5.9079. Min Act: -0.1700

Data Index: 113141 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.7516. Min Act: -0.1700

Data Index: 350382 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.7516. Min Act: -0.1700

Data Index: 1332536 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6891. Min Act: -0.1700

Data Index: 5210 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6579. Min Act: -0.1700

Data Index: 1062669 (C4 (Web Text))

Max Activating Token Index: 501

Text #5

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.7204. Min Act: -0.1700

Data Index: 118220 (C4 (Web Text))

Max Activating Token Index: 82

Text #6

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6579. Min Act: -0.1700

Data Index: 954343 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6579. Min Act: -0.1700

Data Index: 458923 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.7204. Min Act: -0.1700

Data Index: 1088027 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.7204. Min Act: -0.1700

Data Index: 701219 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6891. Min Act: -0.1700

Data Index: 574184 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5954. Min Act: -0.1700

Data Index: 459464 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5954. Min Act: -0.1700

Data Index: 870754 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6266. Min Act: -0.1700

Data Index: 299747 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.6266. Min Act: -0.1700

Data Index: 637132 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5641. Min Act: -0.1700

Data Index: 476555 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5329. Min Act: -0.1700

Data Index: 476386 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5016. Min Act: -0.1700

Data Index: 353032 (C4 (Web Text))

Max Activating Token Index: 120

Text #18

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5329. Min Act: -0.1700

Data Index: 1258666 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 5.9079. Min Range: -5.9079

Max Act: 5.5641. Min Act: -0.1700

Data Index: 1288055 (C4 (Web Text))

Max Activating Token Index: 281