Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 865 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.8186. Min Act: -0.1700

Data Index: 150696 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.7873. Min Act: -0.1700

Data Index: 354830 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.6623. Min Act: -0.1700

Data Index: 375673 (C4 (Web Text))

Max Activating Token Index: 205

Text #3

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.6311. Min Act: -0.1700

Data Index: 1242548 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.6623. Min Act: -0.1700

Data Index: 1284115 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.5998. Min Act: -0.1700

Data Index: 35914 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.5998. Min Act: -0.1700

Data Index: 306868 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.5686. Min Act: -0.1700

Data Index: 1270787 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.5373. Min Act: -0.1700

Data Index: 316570 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.5061. Min Act: -0.1700

Data Index: 836328 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.4436. Min Act: -0.1700

Data Index: 821663 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3498. Min Act: -0.1700

Data Index: 494435 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3498. Min Act: -0.1700

Data Index: 86745 (C4 (Web Text))

Max Activating Token Index: 105

Text #13

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3811. Min Act: -0.1700

Data Index: 561954 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3498. Min Act: -0.1700

Data Index: 869664 (C4 (Web Text))

Max Activating Token Index: 534

Text #15

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3186. Min Act: -0.1700

Data Index: 206933 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3811. Min Act: -0.1700

Data Index: 1147518 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3498. Min Act: -0.1700

Data Index: 732951 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.2873. Min Act: -0.1700

Data Index: 180964 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 5.8186. Min Range: -5.8186

Max Act: 5.3186. Min Act: -0.1700

Data Index: 160156 (C4 (Web Text))

Max Activating Token Index: 548