Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1586 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.2533. Min Act: -0.1700

Data Index: 666567 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.2204. Min Act: -0.1700

Data Index: 355440 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.2073. Min Act: -0.1700

Data Index: 60954 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1889. Min Act: -0.1700

Data Index: 82594 (C4 (Web Text))

Max Activating Token Index: 601

Text #4

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1928. Min Act: -0.1700

Data Index: 116906 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1776. Min Act: -0.1700

Data Index: 1058424 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1660. Min Act: -0.1700

Data Index: 571978 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1845. Min Act: -0.1700

Data Index: 785830 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1879. Min Act: -0.1700

Data Index: 318928 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1405. Min Act: -0.1700

Data Index: 833428 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1340. Min Act: -0.1700

Data Index: 66677 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1278457 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1503. Min Act: -0.1700

Data Index: 968809 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1313. Min Act: -0.1700

Data Index: 1345085 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1071. Min Act: -0.1700

Data Index: 886613 (C4 (Web Text))

Max Activating Token Index: 788

Text #15

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1029. Min Act: -0.1700

Data Index: 952590 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1193. Min Act: -0.1700

Data Index: 191896 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1002. Min Act: -0.1700

Data Index: 109239 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.0968. Min Act: -0.1700

Data Index: 630706 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 3.2533. Min Range: -3.2533

Max Act: 3.1052. Min Act: -0.1700

Data Index: 961306 (C4 (Web Text))

Max Activating Token Index: 801