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

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

Neuron 1290 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: 3.6844. Min Range: -3.6844

Max Act: 3.6844. Min Act: -0.1700

Data Index: 949807 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6180. Min Act: -0.1700

Data Index: 923338 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.6073. Min Act: -0.1700

Data Index: 214686 (C4 (Web Text))

Max Activating Token Index: 748

Text #3

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5276. Min Act: -0.1700

Data Index: 489270 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5181. Min Act: -0.1700

Data Index: 233460 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5234. Min Act: -0.1700

Data Index: 903097 (C4 (Web Text))

Max Activating Token Index: 562

Text #6

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.5012. Min Act: -0.1700

Data Index: 4793 (C4 (Web Text))

Max Activating Token Index: 783

Text #7

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4773. Min Act: -0.1700

Data Index: 801205 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4487. Min Act: -0.1700

Data Index: 450232 (C4 (Web Text))

Max Activating Token Index: 517

Text #9

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4436. Min Act: -0.1700

Data Index: 640409 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4390. Min Act: -0.1700

Data Index: 119870 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4150. Min Act: -0.1700

Data Index: 586020 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.4188. Min Act: -0.1700

Data Index: 287750 (C4 (Web Text))

Max Activating Token Index: 1015

Text #13

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3359. Min Act: -0.1700

Data Index: 1266901 (C4 (Web Text))

Max Activating Token Index: 393

Text #14

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3694. Min Act: -0.1700

Data Index: 188802 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3685. Min Act: -0.1700

Data Index: 989119 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3859. Min Act: -0.1700

Data Index: 62842 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3625. Min Act: -0.1700

Data Index: 611073 (C4 (Web Text))

Max Activating Token Index: 737

Text #18

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3515. Min Act: -0.1700

Data Index: 539098 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 3.6844. Min Range: -3.6844

Max Act: 3.3447. Min Act: -0.1700

Data Index: 564602 (C4 (Web Text))

Max Activating Token Index: 385