Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1526 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.1027. Min Act: -0.1700

Data Index: 692102 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0869. Min Act: -0.1700

Data Index: 20449 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0711. Min Act: -0.1700

Data Index: 897767 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0869. Min Act: -0.1700

Data Index: 1090264 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0869. Min Act: -0.1700

Data Index: 1156779 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0711. Min Act: -0.1700

Data Index: 425995 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0553. Min Act: -0.1700

Data Index: 1306170 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0553. Min Act: -0.1700

Data Index: 612273 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0238. Min Act: -0.1700

Data Index: 573168 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0238. Min Act: -0.1700

Data Index: 4107 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 3.1027. Min Range: -3.1027

Max Act: 2.9921. Min Act: -0.1700

Data Index: 406241 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0238. Min Act: -0.1700

Data Index: 1336914 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0080. Min Act: -0.1700

Data Index: 3588 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 3.1027. Min Range: -3.1027

Max Act: 2.9921. Min Act: -0.1700

Data Index: 525550 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0080. Min Act: -0.1700

Data Index: 81752 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 3.1027. Min Range: -3.1027

Max Act: 2.9921. Min Act: -0.1700

Data Index: 467098 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 3.1027. Min Range: -3.1027

Max Act: 2.9921. Min Act: -0.1700

Data Index: 150197 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 3.1027. Min Range: -3.1027

Max Act: 2.9921. Min Act: -0.1700

Data Index: 851200 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 3.1027. Min Range: -3.1027

Max Act: 2.9763. Min Act: -0.1700

Data Index: 113483 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.1027. Min Range: -3.1027

Max Act: 3.0080. Min Act: -0.1700

Data Index: 369422 (C4 (Web Text))

Max Activating Token Index: 560