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

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

Neuron 996 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.1659. Min Act: -0.1700

Data Index: 1044574 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.1034. Min Act: -0.1700

Data Index: 691403 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.1659. Min Act: -0.1700

Data Index: 1120905 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0409. Min Act: -0.1700

Data Index: 112755 (C4 (Web Text))

Max Activating Token Index: 269

Text #4

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.1346. Min Act: -0.1700

Data Index: 1290784 (C4 (Web Text))

Max Activating Token Index: 339

Text #5

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0409. Min Act: -0.1700

Data Index: 748789 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.1034. Min Act: -0.1700

Data Index: 1194684 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0096. Min Act: -0.1700

Data Index: 651809 (C4 (Web Text))

Max Activating Token Index: 717

Text #8

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0096. Min Act: -0.1700

Data Index: 608884 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0721. Min Act: -0.1700

Data Index: 323733 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0096. Min Act: -0.1700

Data Index: 1205682 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 5.1659. Min Range: -5.1659

Max Act: 5.0721. Min Act: -0.1700

Data Index: 686145 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9784. Min Act: -0.1700

Data Index: 17822 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9784. Min Act: -0.1700

Data Index: 785450 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9784. Min Act: -0.1700

Data Index: 864692 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9159. Min Act: -0.1700

Data Index: 501174 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9471. Min Act: -0.1700

Data Index: 554508 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.8846. Min Act: -0.1700

Data Index: 417904 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9784. Min Act: -0.1700

Data Index: 1131111 (C4 (Web Text))

Max Activating Token Index: 269

Text #19

Max Range: 5.1659. Min Range: -5.1659

Max Act: 4.9159. Min Act: -0.1700

Data Index: 1103749 (C4 (Web Text))

Max Activating Token Index: 981