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

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

Neuron 180 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: 5.1683. Min Range: -5.1683

Max Act: 5.1683. Min Act: -0.1700

Data Index: 803193 (C4 (Web Text))

Max Activating Token Index: 672

Text #1

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1683. Min Act: -0.1700

Data Index: 617127 (C4 (Web Text))

Max Activating Token Index: 793

Text #2

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1371. Min Act: -0.1700

Data Index: 529698 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1683. Min Act: -0.1700

Data Index: 741421 (C4 (Web Text))

Max Activating Token Index: 472

Text #4

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1058. Min Act: -0.1700

Data Index: 390492 (C4 (Web Text))

Max Activating Token Index: 755

Text #5

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1371. Min Act: -0.1700

Data Index: 454006 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1371. Min Act: -0.1700

Data Index: 1199379 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1683. Min Act: -0.1700

Data Index: 448178 (C4 (Web Text))

Max Activating Token Index: 577

Text #8

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1683. Min Act: -0.1700

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 495

Text #9

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1058. Min Act: -0.1700

Data Index: 1344969 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0746. Min Act: -0.1700

Data Index: 394344 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.1371. Min Act: -0.1700

Data Index: 1299205 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0746. Min Act: -0.1700

Data Index: 1087145 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0121. Min Act: -0.1700

Data Index: 543283 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0433. Min Act: -0.1700

Data Index: 849972 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0746. Min Act: -0.1700

Data Index: 884621 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0433. Min Act: -0.1700

Data Index: 917085 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0433. Min Act: -0.1700

Data Index: 175185 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0746. Min Act: -0.1700

Data Index: 515937 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 5.1683. Min Range: -5.1683

Max Act: 5.0746. Min Act: -0.1700

Data Index: 301003 (C4 (Web Text))

Max Activating Token Index: 799