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

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

Neuron 1711 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.5025. Min Act: -0.1699

Data Index: 1137924 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.5338. Min Act: -0.1700

Data Index: 1099093 (C4 (Web Text))

Max Activating Token Index: 318

Text #2

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.5025. Min Act: -0.1700

Data Index: 934243 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.3775. Min Act: -0.1700

Data Index: 57888 (C4 (Web Text))

Max Activating Token Index: 694

Text #4

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.2213. Min Act: -0.1700

Data Index: 588066 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.1900. Min Act: -0.1700

Data Index: 899184 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0650. Min Act: -0.1700

Data Index: 877081 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0025. Min Act: -0.1700

Data Index: 998424 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0650. Min Act: -0.1700

Data Index: 890504 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0338. Min Act: -0.1699

Data Index: 949419 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0650. Min Act: -0.1700

Data Index: 644464 (C4 (Web Text))

Max Activating Token Index: 386

Text #11

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0025. Min Act: -0.1700

Data Index: 67473 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 8.5338. Min Range: -8.5338

Max Act: 8.0025. Min Act: -0.1700

Data Index: 1275493 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.9713. Min Act: -0.1700

Data Index: 35831 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.8150. Min Act: -0.1700

Data Index: 581162 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.9400. Min Act: -0.1700

Data Index: 1041855 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.7838. Min Act: -0.1699

Data Index: 700689 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.7838. Min Act: -0.1700

Data Index: 1330219 (C4 (Web Text))

Max Activating Token Index: 59

Text #18

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.7525. Min Act: -0.1700

Data Index: 217183 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 8.5338. Min Range: -8.5338

Max Act: 7.7838. Min Act: -0.1700

Data Index: 640387 (C4 (Web Text))

Max Activating Token Index: 879