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

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

Neuron 1592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.8846. Min Act: -0.1700

Data Index: 581347 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.8534. Min Act: -0.1700

Data Index: 662717 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.8221. Min Act: -0.1700

Data Index: 843936 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.7284. Min Act: -0.1700

Data Index: 1285462 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.6346. Min Act: -0.1700

Data Index: 798241 (C4 (Web Text))

Max Activating Token Index: 439

Text #5

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.5721. Min Act: -0.1700

Data Index: 913423 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.5409. Min Act: -0.1700

Data Index: 1143990 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.5409. Min Act: -0.1700

Data Index: 923912 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.5409. Min Act: -0.1700

Data Index: 649058 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.5096. Min Act: -0.1700

Data Index: 122800 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4784. Min Act: -0.1700

Data Index: 458311 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.5096. Min Act: -0.1700

Data Index: 594052 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4159. Min Act: -0.1700

Data Index: 1043836 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4471. Min Act: -0.1700

Data Index: 1211816 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4159. Min Act: -0.1700

Data Index: 772900 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4784. Min Act: -0.1700

Data Index: 291582 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.3846. Min Act: -0.1700

Data Index: 507553 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.3534. Min Act: -0.1700

Data Index: 282141 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4159. Min Act: -0.1700

Data Index: 624862 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 5.8846. Min Range: -5.8846

Max Act: 5.4471. Min Act: -0.1700

Data Index: 1133328 (C4 (Web Text))

Max Activating Token Index: 320