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

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

Neuron 498 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.6738. Min Act: -0.1700

Data Index: 464822 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.4859. Min Act: -0.1700

Data Index: 725238 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.4232. Min Act: -0.1700

Data Index: 36331 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.4075. Min Act: -0.1700

Data Index: 287640 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.3291. Min Act: -0.1700

Data Index: 940577 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.3448. Min Act: -0.1700

Data Index: 1159777 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2820. Min Act: -0.1700

Data Index: 242946 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2820. Min Act: -0.1700

Data Index: 312697 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2663. Min Act: -0.1700

Data Index: 121286 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2663. Min Act: -0.1700

Data Index: 1258763 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2348. Min Act: -0.1700

Data Index: 770778 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2505. Min Act: -0.1700

Data Index: 387304 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2191. Min Act: -0.1700

Data Index: 99418 (C4 (Web Text))

Max Activating Token Index: 408

Text #13

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2505. Min Act: -0.1700

Data Index: 1274807 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2191. Min Act: -0.1700

Data Index: 933299 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2191. Min Act: -0.1700

Data Index: 676068 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2191. Min Act: -0.1700

Data Index: 1010282 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2191. Min Act: -0.1700

Data Index: 292280 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2348. Min Act: -0.1700

Data Index: 1056452 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 3.6738. Min Range: -3.6738

Max Act: 3.2191. Min Act: -0.1700

Data Index: 955894 (C4 (Web Text))

Max Activating Token Index: 457