Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1349 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0014. Min Range: -5.0014

Max Act: 5.0014. Min Act: -0.1700

Data Index: 1080921 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.8764. Min Act: -0.1700

Data Index: 45227 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.9077. Min Act: -0.1700

Data Index: 221885 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.8452. Min Act: -0.1700

Data Index: 595416 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7514. Min Act: -0.1700

Data Index: 870679 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.8764. Min Act: -0.1700

Data Index: 9318 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7827. Min Act: -0.1700

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7514. Min Act: -0.1700

Data Index: 1016816 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7514. Min Act: -0.1700

Data Index: 1156311 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.6576. Min Act: -0.1700

Data Index: 592798 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7827. Min Act: -0.1700

Data Index: 1108525 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7514. Min Act: -0.1700

Data Index: 991483 (C4 (Web Text))

Max Activating Token Index: 336

Text #12

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7201. Min Act: -0.1700

Data Index: 1358015 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.6576. Min Act: -0.1700

Data Index: 22398 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.5639. Min Act: -0.1700

Data Index: 1018588 (C4 (Web Text))

Max Activating Token Index: 372

Text #15

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.5951. Min Act: -0.1700

Data Index: 280602 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.6264. Min Act: -0.1700

Data Index: 881084 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.6576. Min Act: -0.1700

Data Index: 1038397 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7827. Min Act: -0.1700

Data Index: 236054 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 5.0014. Min Range: -5.0014

Max Act: 4.7201. Min Act: -0.1700

Data Index: 907164 (C4 (Web Text))

Max Activating Token Index: 699