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

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

Neuron 116 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: 3.4670. Min Range: -3.4670

Max Act: 3.4490. Min Act: -0.1700

Data Index: 698750 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.4670. Min Act: -0.1700

Data Index: 430559 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3283. Min Act: -0.1700

Data Index: 92246 (C4 (Web Text))

Max Activating Token Index: 580

Text #3

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3673. Min Act: -0.1700

Data Index: 340273 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3993. Min Act: -0.1700

Data Index: 266895 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3392. Min Act: -0.1700

Data Index: 639486 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3518. Min Act: -0.1700

Data Index: 1398664 (Python Code)

Max Activating Token Index: 195

Text #7

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2370. Min Act: -0.1700

Data Index: 239524 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3275. Min Act: -0.1700

Data Index: 636742 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3538. Min Act: -0.1700

Data Index: 762011 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3246. Min Act: -0.1700

Data Index: 548782 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2535. Min Act: -0.1700

Data Index: 714282 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2773. Min Act: -0.1700

Data Index: 12817 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1656717 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2663. Min Act: -0.1700

Data Index: 1229559 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2116. Min Act: -0.1700

Data Index: 485237 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2756. Min Act: -0.1700

Data Index: 402552 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2685. Min Act: -0.1700

Data Index: 301527 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.3073. Min Act: -0.1700

Data Index: 782121 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 3.4670. Min Range: -3.4670

Max Act: 3.2911. Min Act: -0.1700

Data Index: 1280986 (C4 (Web Text))

Max Activating Token Index: 748