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

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

Neuron 1364 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: 5.0757. Min Range: -5.0757

Max Act: 5.0757. Min Act: -0.1700

Data Index: 56633 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.9819. Min Act: -0.1700

Data Index: 1065773 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.9819. Min Act: -0.1700

Data Index: 471005 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.8569. Min Act: -0.1700

Data Index: 553541 (C4 (Web Text))

Max Activating Token Index: 618

Text #4

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.8257. Min Act: -0.1700

Data Index: 1100021 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7944. Min Act: -0.1700

Data Index: 141549 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7632. Min Act: -0.1700

Data Index: 98408 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7632. Min Act: -0.1700

Data Index: 633154 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.6694. Min Act: -0.1700

Data Index: 1008821 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7007. Min Act: -0.1700

Data Index: 494080 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7319. Min Act: -0.1700

Data Index: 869822 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7632. Min Act: -0.1700

Data Index: 261226 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7007. Min Act: -0.1700

Data Index: 1261909 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7007. Min Act: -0.1700

Data Index: 870965 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7007. Min Act: -0.1700

Data Index: 273373 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.6694. Min Act: -0.1700

Data Index: 1288426 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.6382. Min Act: -0.1700

Data Index: 319420 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.6694. Min Act: -0.1700

Data Index: 551447 (C4 (Web Text))

Max Activating Token Index: 294

Text #18

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.6069. Min Act: -0.1700

Data Index: 823397 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 5.0757. Min Range: -5.0757

Max Act: 4.7007. Min Act: -0.1700

Data Index: 811947 (C4 (Web Text))

Max Activating Token Index: 515