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

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

Neuron 808 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: 5.3741. Min Range: -5.3741

Max Act: 5.3741. Min Act: -0.1700

Data Index: 453239 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.3429. Min Act: -0.1700

Data Index: 550237 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.2491. Min Act: -0.1700

Data Index: 81604 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.2491. Min Act: -0.1700

Data Index: 308502 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1041698 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.2491. Min Act: -0.1700

Data Index: 826726 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.1554. Min Act: -0.1700

Data Index: 1032939 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.1866. Min Act: -0.1700

Data Index: 1067639 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0929. Min Act: -0.1700

Data Index: 1331323 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0616. Min Act: -0.1699

Data Index: 571974 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.1241. Min Act: -0.1700

Data Index: 193182 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0929. Min Act: -0.1700

Data Index: 867 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0304. Min Act: -0.1700

Data Index: 717882 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0616. Min Act: -0.1700

Data Index: 901710 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0616. Min Act: -0.1700

Data Index: 77015 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0616. Min Act: -0.1700

Data Index: 768717 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0616. Min Act: -0.1700

Data Index: 1118458 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 5.3741. Min Range: -5.3741

Max Act: 5.0304. Min Act: -0.1700

Data Index: 702079 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 5.3741. Min Range: -5.3741

Max Act: 4.9991. Min Act: -0.1700

Data Index: 788795 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 5.3741. Min Range: -5.3741

Max Act: 4.9679. Min Act: -0.1700

Data Index: 506035 (C4 (Web Text))

Max Activating Token Index: 756