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

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

Neuron 1321 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: 5.2719. Min Range: -5.2719

Max Act: 5.2719. Min Act: -0.1700

Data Index: 76673 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 5.2719. Min Range: -5.2719

Max Act: 5.1469. Min Act: -0.1700

Data Index: 367052 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 5.2719. Min Range: -5.2719

Max Act: 5.0219. Min Act: -0.1700

Data Index: 331300 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.9594. Min Act: -0.1700

Data Index: 994613 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.8969. Min Act: -0.1700

Data Index: 34391 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.8344. Min Act: -0.1700

Data Index: 108126 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.8032. Min Act: -0.1700

Data Index: 1280517 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.8032. Min Act: -0.1700

Data Index: 190910 (C4 (Web Text))

Max Activating Token Index: 465

Text #8

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.7719. Min Act: -0.1700

Data Index: 276664 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.7719. Min Act: -0.1700

Data Index: 1072119 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.7719. Min Act: -0.1700

Data Index: 338902 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6938. Min Act: -0.1700

Data Index: 183924 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.7094. Min Act: -0.1700

Data Index: 714423 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6938. Min Act: -0.1700

Data Index: 857161 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6782. Min Act: -0.1700

Data Index: 1353242 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6782. Min Act: -0.1700

Data Index: 500216 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6782. Min Act: -0.1700

Data Index: 1010782 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6782. Min Act: -0.1700

Data Index: 282103 (C4 (Web Text))

Max Activating Token Index: 387

Text #18

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.6626. Min Act: -0.1700

Data Index: 554586 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 5.2719. Min Range: -5.2719

Max Act: 4.5376. Min Act: -0.1700

Data Index: 916865 (C4 (Web Text))

Max Activating Token Index: 841