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

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

Neuron 1137 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: 2.8498. Min Range: -2.8498

Max Act: 2.8498. Min Act: -0.1661

Data Index: 1639633 (Python Code)

Max Activating Token Index: 828

Text #1

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.7548. Min Act: -0.1700

Data Index: 481961 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.7015. Min Act: -0.1700

Data Index: 412673 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.7049. Min Act: -0.1700

Data Index: 830771 (C4 (Web Text))

Max Activating Token Index: 1006

Text #4

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6837. Min Act: -0.1700

Data Index: 151046 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6584. Min Act: -0.1700

Data Index: 552403 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6380. Min Act: -0.1700

Data Index: 303357 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6200. Min Act: -0.1700

Data Index: 828439 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6265. Min Act: -0.1700

Data Index: 245017 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5894. Min Act: -0.1700

Data Index: 146900 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6051. Min Act: -0.1700

Data Index: 1080409 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.6049. Min Act: -0.1700

Data Index: 1028649 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5928. Min Act: -0.1700

Data Index: 642428 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5961. Min Act: -0.1700

Data Index: 620307 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5956. Min Act: -0.1700

Data Index: 348136 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5765. Min Act: -0.1700

Data Index: 756820 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5736. Min Act: -0.1700

Data Index: 278914 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5806. Min Act: -0.1700

Data Index: 902686 (C4 (Web Text))

Max Activating Token Index: 170

Text #18

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5761. Min Act: -0.1700

Data Index: 1092116 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 2.8498. Min Range: -2.8498

Max Act: 2.5706. Min Act: -0.1700

Data Index: 1047822 (C4 (Web Text))

Max Activating Token Index: 971