Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1594 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.9017. Min Act: -0.1700

Data Index: 1279485 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.5575. Min Act: -0.1700

Data Index: 282338 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.4635. Min Act: -0.1700

Data Index: 366619 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.4321. Min Act: -0.1700

Data Index: 1210575 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.4008. Min Act: -0.1700

Data Index: 351989 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.4008. Min Act: -0.1700

Data Index: 404636 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.4008. Min Act: -0.1700

Data Index: 819940 (C4 (Web Text))

Max Activating Token Index: 528

Text #7

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3380. Min Act: -0.1700

Data Index: 525823 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3380. Min Act: -0.1700

Data Index: 259850 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3066. Min Act: -0.1700

Data Index: 275000 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1211766 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3380. Min Act: -0.1700

Data Index: 1228474 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3066. Min Act: -0.1700

Data Index: 1204817 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3380. Min Act: -0.1700

Data Index: 809150 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3066. Min Act: -0.1700

Data Index: 833413 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3066. Min Act: -0.1700

Data Index: 505340 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.3380. Min Act: -0.1700

Data Index: 871769 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.2752. Min Act: -0.1700

Data Index: 242460 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.2752. Min Act: -0.1700

Data Index: 286135 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 3.9017. Min Range: -3.9017

Max Act: 3.2752. Min Act: -0.1700

Data Index: 57044 (C4 (Web Text))

Max Activating Token Index: 709