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

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

Neuron 1629 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.8521. Min Act: -0.1700

Data Index: 121547 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.6957. Min Act: -0.1700

Data Index: 1115511 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.6331. Min Act: -0.1700

Data Index: 460247 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.6018. Min Act: -0.1700

Data Index: 31923 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.6644. Min Act: -0.1700

Data Index: 213857 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5704. Min Act: -0.1700

Data Index: 70708 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5704. Min Act: -0.1700

Data Index: 930413 (C4 (Web Text))

Max Activating Token Index: 188

Text #7

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5078. Min Act: -0.1700

Data Index: 672948 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5078. Min Act: -0.1700

Data Index: 279459 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5704. Min Act: -0.1700

Data Index: 708544 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5704. Min Act: -0.1699

Data Index: 674513 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5391. Min Act: -0.1700

Data Index: 374096 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5391. Min Act: -0.1700

Data Index: 1315878 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5078. Min Act: -0.1700

Data Index: 525113 (C4 (Web Text))

Max Activating Token Index: 957

Text #14

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5078. Min Act: -0.1700

Data Index: 750854 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5391. Min Act: -0.1700

Data Index: 396342 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5391. Min Act: -0.1700

Data Index: 321959 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5078. Min Act: -0.1700

Data Index: 783612 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.5391. Min Act: -0.1700

Data Index: 272280 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 3.8521. Min Range: -3.8521

Max Act: 3.4764. Min Act: -0.1700

Data Index: 704879 (C4 (Web Text))

Max Activating Token Index: 515