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

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

Neuron 312 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: 3.8833. Min Range: -3.8833

Max Act: 3.8833. Min Act: -0.1700

Data Index: 224197 (C4 (Web Text))

Max Activating Token Index: 549

Text #1

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.7581. Min Act: -0.1700

Data Index: 508394 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.8207. Min Act: -0.1700

Data Index: 1082217 (C4 (Web Text))

Max Activating Token Index: 886

Text #3

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6329. Min Act: -0.1700

Data Index: 1201876 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6016. Min Act: -0.1700

Data Index: 1328973 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6329. Min Act: -0.1700

Data Index: 880688 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6329. Min Act: -0.1700

Data Index: 1179888 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6016. Min Act: -0.1700

Data Index: 650688 (C4 (Web Text))

Max Activating Token Index: 855

Text #8

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6016. Min Act: -0.1700

Data Index: 324145 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.6016. Min Act: -0.1700

Data Index: 377088 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5703. Min Act: -0.1700

Data Index: 516934 (C4 (Web Text))

Max Activating Token Index: 550

Text #11

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5703. Min Act: -0.1700

Data Index: 1023435 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5703. Min Act: -0.1700

Data Index: 633358 (C4 (Web Text))

Max Activating Token Index: 719

Text #13

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5390. Min Act: -0.1700

Data Index: 1327873 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5077. Min Act: -0.1700

Data Index: 654490 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5077. Min Act: -0.1700

Data Index: 507513 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.4763. Min Act: -0.1700

Data Index: 651259 (C4 (Web Text))

Max Activating Token Index: 376

Text #17

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5390. Min Act: -0.1700

Data Index: 1099344 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5077. Min Act: -0.1700

Data Index: 416906 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 3.8833. Min Range: -3.8833

Max Act: 3.5390. Min Act: -0.1700

Data Index: 385807 (C4 (Web Text))

Max Activating Token Index: 111