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

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

Neuron 1710 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: 3.5568. Min Range: -3.5568

Max Act: 3.5568. Min Act: -0.1700

Data Index: 369567 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.5057. Min Act: -0.1700

Data Index: 652923 (C4 (Web Text))

Max Activating Token Index: 1017

Text #2

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4502. Min Act: -0.1700

Data Index: 713631 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4399. Min Act: -0.1700

Data Index: 82640 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4258. Min Act: -0.1700

Data Index: 1158661 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4203. Min Act: -0.1700

Data Index: 528745 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4275. Min Act: -0.1700

Data Index: 715569 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4196. Min Act: -0.1700

Data Index: 1227549 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4155. Min Act: -0.1700

Data Index: 420085 (C4 (Web Text))

Max Activating Token Index: 16

Text #9

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4247. Min Act: -0.1700

Data Index: 33401 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4044. Min Act: -0.1700

Data Index: 776838 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4017. Min Act: -0.1700

Data Index: 453124 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3998. Min Act: -0.1700

Data Index: 560302 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.4104. Min Act: -0.1700

Data Index: 548398 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3888. Min Act: -0.1700

Data Index: 906455 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3908. Min Act: -0.1700

Data Index: 428040 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3769. Min Act: -0.1700

Data Index: 594689 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3924. Min Act: -0.1700

Data Index: 1296873 (C4 (Web Text))

Max Activating Token Index: 473

Text #18

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3717. Min Act: -0.1700

Data Index: 1062762 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 3.5568. Min Range: -3.5568

Max Act: 3.3665. Min Act: -0.1700

Data Index: 584691 (C4 (Web Text))

Max Activating Token Index: 979