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

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

Neuron 1935 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: 3.9714. Min Range: -3.9714

Max Act: 3.9714. Min Act: -0.1700

Data Index: 187617 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.9154. Min Act: -0.1700

Data Index: 172003 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.8990. Min Act: -0.1700

Data Index: 802337 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.8378. Min Act: -0.1700

Data Index: 222845 (C4 (Web Text))

Max Activating Token Index: 895

Text #4

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7229. Min Act: -0.1700

Data Index: 14696 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7732. Min Act: -0.1700

Data Index: 932101 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7247. Min Act: -0.1700

Data Index: 594940 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7442. Min Act: -0.1700

Data Index: 416486 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7514. Min Act: -0.1700

Data Index: 765242 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7515. Min Act: -0.1700

Data Index: 30712 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6927. Min Act: -0.1700

Data Index: 376815 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7361. Min Act: -0.1700

Data Index: 914267 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7613. Min Act: -0.1700

Data Index: 315170 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6988. Min Act: -0.1700

Data Index: 153711 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7179. Min Act: -0.1700

Data Index: 775379 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6908. Min Act: -0.1700

Data Index: 872174 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6771. Min Act: -0.1700

Data Index: 894393 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6727. Min Act: -0.1700

Data Index: 474577 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.6824. Min Act: -0.1700

Data Index: 407912 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 3.9714. Min Range: -3.9714

Max Act: 3.7073. Min Act: -0.1700

Data Index: 190151 (C4 (Web Text))

Max Activating Token Index: 486