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

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

Neuron 914 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: 3.7500. Min Range: -3.7500

Max Act: 3.7500. Min Act: -0.1700

Data Index: 756635 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.6092. Min Act: -0.1700

Data Index: 804037 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.5465. Min Act: -0.1700

Data Index: 861763 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.5778. Min Act: -0.1700

Data Index: 1206670 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.5622. Min Act: -0.1700

Data Index: 1009484 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.5309. Min Act: -0.1700

Data Index: 897308 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4995. Min Act: -0.1700

Data Index: 921324 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4839. Min Act: -0.1700

Data Index: 1242393 (C4 (Web Text))

Max Activating Token Index: 293

Text #8

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4839. Min Act: -0.1700

Data Index: 621062 (C4 (Web Text))

Max Activating Token Index: 409

Text #9

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4839. Min Act: -0.1700

Data Index: 447575 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4525. Min Act: -0.1700

Data Index: 431561 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4525. Min Act: -0.1700

Data Index: 643487 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4525. Min Act: -0.1700

Data Index: 1304718 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4525. Min Act: -0.1700

Data Index: 274911 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4525. Min Act: -0.1700

Data Index: 266091 (C4 (Web Text))

Max Activating Token Index: 528

Text #15

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4368. Min Act: -0.1700

Data Index: 456211 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4368. Min Act: -0.1700

Data Index: 514145 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4211. Min Act: -0.1700

Data Index: 1322890 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4211. Min Act: -0.1700

Data Index: 414981 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 3.7500. Min Range: -3.7500

Max Act: 3.4211. Min Act: -0.1700

Data Index: 401266 (C4 (Web Text))

Max Activating Token Index: 657