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

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

Neuron 19 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: 3.3145. Min Range: -3.3145

Max Act: 3.3145. Min Act: -0.1700

Data Index: 1089259 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2713. Min Act: -0.1700

Data Index: 404586 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2705. Min Act: -0.1700

Data Index: 978413 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.2246. Min Act: -0.1700

Data Index: 387074 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1525. Min Act: -0.1700

Data Index: 160889 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1583. Min Act: -0.1700

Data Index: 559526 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1237. Min Act: -0.1700

Data Index: 1341073 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1069. Min Act: -0.1700

Data Index: 996107 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.1252. Min Act: -0.1700

Data Index: 140682 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0714. Min Act: -0.1700

Data Index: 999 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0560. Min Act: -0.1700

Data Index: 102976 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0374. Min Act: -0.1700

Data Index: 154785 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0671. Min Act: -0.1700

Data Index: 1065101 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0711. Min Act: -0.1700

Data Index: 460203 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0381. Min Act: -0.1700

Data Index: 1151317 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0242. Min Act: -0.1700

Data Index: 274686 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0275. Min Act: -0.1700

Data Index: 321558 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 3.3145. Min Range: -3.3145

Max Act: 3.0229. Min Act: -0.1700

Data Index: 607219 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 3.3145. Min Range: -3.3145

Max Act: 2.9785. Min Act: -0.1700

Data Index: 87457 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 3.3145. Min Range: -3.3145

Max Act: 2.9866. Min Act: -0.1700

Data Index: 865976 (C4 (Web Text))

Max Activating Token Index: 685