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

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

Neuron 1322 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.9263. Min Act: -0.1700

Data Index: 759833 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8638. Min Act: -0.1700

Data Index: 109849 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1335151 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8325. Min Act: -0.1700

Data Index: 932413 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8951. Min Act: -0.1700

Data Index: 1154120 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8951. Min Act: -0.1700

Data Index: 127699 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8012. Min Act: -0.1700

Data Index: 571593 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8325. Min Act: -0.1700

Data Index: 515216 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8012. Min Act: -0.1700

Data Index: 667585 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8638. Min Act: -0.1700

Data Index: 100356 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8012. Min Act: -0.1700

Data Index: 787241 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8325. Min Act: -0.1700

Data Index: 928696 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8325. Min Act: -0.1700

Data Index: 241187 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8012. Min Act: -0.1700

Data Index: 1167776 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.7699. Min Act: -0.1700

Data Index: 360271 (C4 (Web Text))

Max Activating Token Index: 800

Text #15

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8012. Min Act: -0.1700

Data Index: 993229 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.7699. Min Act: -0.1700

Data Index: 200254 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.7387. Min Act: -0.1700

Data Index: 196504 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.8012. Min Act: -0.1700

Data Index: 350076 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 3.9263. Min Range: -3.9263

Max Act: 3.7387. Min Act: -0.1700

Data Index: 843907 (C4 (Web Text))

Max Activating Token Index: 893