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

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

Neuron 1720 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.2417. Min Act: -0.1700

Data Index: 21590 (C4 (Web Text))

Max Activating Token Index: 424

Text #1

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.2260. Min Act: -0.1700

Data Index: 1251224 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.2417. Min Act: -0.1700

Data Index: 642240 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1630. Min Act: -0.1700

Data Index: 776602 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.2102. Min Act: -0.1700

Data Index: 1213831 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1788. Min Act: -0.1700

Data Index: 947365 (C4 (Web Text))

Max Activating Token Index: 744

Text #6

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1473. Min Act: -0.1700

Data Index: 347639 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1630. Min Act: -0.1700

Data Index: 965034 (C4 (Web Text))

Max Activating Token Index: 442

Text #8

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1315. Min Act: -0.1700

Data Index: 826839 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1315. Min Act: -0.1700

Data Index: 1306302 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1158. Min Act: -0.1700

Data Index: 1161965 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.1158. Min Act: -0.1700

Data Index: 91363 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0842. Min Act: -0.1700

Data Index: 632108 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0685. Min Act: -0.1700

Data Index: 1342743 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0685. Min Act: -0.1700

Data Index: 1053521 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0685. Min Act: -0.1700

Data Index: 734922 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0685. Min Act: -0.1700

Data Index: 443957 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0685. Min Act: -0.1700

Data Index: 1147271 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0685. Min Act: -0.1700

Data Index: 519319 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 3.2417. Min Range: -3.2417

Max Act: 3.0527. Min Act: -0.1700

Data Index: 502203 (C4 (Web Text))

Max Activating Token Index: 462