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

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

Neuron 536 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: 3.9719. Min Range: -3.9719

Max Act: 3.9719. Min Act: -0.1700

Data Index: 129328 (C4 (Web Text))

Max Activating Token Index: 951

Text #1

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.8715. Min Act: -0.1700

Data Index: 623429 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.8367. Min Act: -0.1700

Data Index: 1344907 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.8092. Min Act: -0.1700

Data Index: 1155183 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.8245. Min Act: -0.1700

Data Index: 163446 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7874. Min Act: -0.1700

Data Index: 875777 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7439. Min Act: -0.1700

Data Index: 89892 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7175. Min Act: -0.1700

Data Index: 454074 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7077. Min Act: -0.1700

Data Index: 253687 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7438. Min Act: -0.1700

Data Index: 653479 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7321. Min Act: -0.1700

Data Index: 818163 (C4 (Web Text))

Max Activating Token Index: 513

Text #11

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.7058. Min Act: -0.1700

Data Index: 542988 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6935. Min Act: -0.1700

Data Index: 766593 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6856. Min Act: -0.1700

Data Index: 149327 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6953. Min Act: -0.1700

Data Index: 39427 (C4 (Web Text))

Max Activating Token Index: 89

Text #15

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6858. Min Act: -0.1700

Data Index: 51566 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6769. Min Act: -0.1700

Data Index: 948945 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6833. Min Act: -0.1700

Data Index: 776314 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6681. Min Act: -0.1700

Data Index: 986643 (C4 (Web Text))

Max Activating Token Index: 937

Text #19

Max Range: 3.9719. Min Range: -3.9719

Max Act: 3.6893. Min Act: -0.1700

Data Index: 171676 (C4 (Web Text))

Max Activating Token Index: 851