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

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

Neuron 532 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: 3.8944. Min Range: -3.8944

Max Act: 3.8944. Min Act: -0.1700

Data Index: 323154 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8631. Min Act: -0.1700

Data Index: 933408 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8006. Min Act: -0.1700

Data Index: 970102 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.8319. Min Act: -0.1700

Data Index: 115894 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7693. Min Act: -0.1700

Data Index: 209258 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7693. Min Act: -0.1700

Data Index: 860851 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7693. Min Act: -0.1700

Data Index: 1194931 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7380. Min Act: -0.1700

Data Index: 1077692 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7380. Min Act: -0.1700

Data Index: 482959 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7067. Min Act: -0.1700

Data Index: 743583 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7067. Min Act: -0.1700

Data Index: 982035 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7380. Min Act: -0.1700

Data Index: 1147558 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7067. Min Act: -0.1700

Data Index: 537835 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6754. Min Act: -0.1700

Data Index: 257175 (C4 (Web Text))

Max Activating Token Index: 72

Text #14

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6754. Min Act: -0.1700

Data Index: 353927 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6754. Min Act: -0.1700

Data Index: 526666 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.7067. Min Act: -0.1700

Data Index: 134820 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6754. Min Act: -0.1700

Data Index: 52535 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6441. Min Act: -0.1700

Data Index: 1175456 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 3.8944. Min Range: -3.8944

Max Act: 3.6441. Min Act: -0.1700

Data Index: 703717 (C4 (Web Text))

Max Activating Token Index: 525