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

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

Neuron 1388 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: 3.2374. Min Range: -3.2374

Max Act: 3.2374. Min Act: -0.1700

Data Index: 115009 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.1587. Min Act: -0.1700

Data Index: 1040716 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.1115. Min Act: -0.1700

Data Index: 185952 (C4 (Web Text))

Max Activating Token Index: 654

Text #3

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0957. Min Act: -0.1700

Data Index: 477543 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0799. Min Act: -0.1700

Data Index: 197895 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0641. Min Act: -0.1700

Data Index: 559939 (C4 (Web Text))

Max Activating Token Index: 670

Text #6

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0326. Min Act: -0.1700

Data Index: 1001665 (C4 (Web Text))

Max Activating Token Index: 519

Text #7

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0168. Min Act: -0.1700

Data Index: 913136 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0010. Min Act: -0.1700

Data Index: 517158 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0168. Min Act: -0.1700

Data Index: 623335 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0168. Min Act: -0.1700

Data Index: 1322607 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0484. Min Act: -0.1700

Data Index: 1077999 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0010. Min Act: -0.1700

Data Index: 779402 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.9693. Min Act: -0.1700

Data Index: 448280 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.9693. Min Act: -0.1700

Data Index: 545136 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.9851. Min Act: -0.1700

Data Index: 319646 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 3.2374. Min Range: -3.2374

Max Act: 3.0010. Min Act: -0.1700

Data Index: 56317 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.9693. Min Act: -0.1700

Data Index: 204477 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.9851. Min Act: -0.1700

Data Index: 508934 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 3.2374. Min Range: -3.2374

Max Act: 2.9693. Min Act: -0.1700

Data Index: 380176 (C4 (Web Text))

Max Activating Token Index: 825