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

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

Neuron 1631 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.9342. Min Act: -0.1700

Data Index: 404553 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.9342. Min Act: -0.1700

Data Index: 568968 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.8717. Min Act: -0.1700

Data Index: 553121 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.8404. Min Act: -0.1700

Data Index: 522810 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.8091. Min Act: -0.1700

Data Index: 222790 (C4 (Web Text))

Max Activating Token Index: 528

Text #5

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.8091. Min Act: -0.1700

Data Index: 1330135 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.7778. Min Act: -0.1700

Data Index: 391342 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.8091. Min Act: -0.1700

Data Index: 560661 (C4 (Web Text))

Max Activating Token Index: 290

Text #8

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.7622. Min Act: -0.1700

Data Index: 905006 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6996. Min Act: -0.1700

Data Index: 106244 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6996. Min Act: -0.1700

Data Index: 1169458 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6683. Min Act: -0.1700

Data Index: 294349 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6840. Min Act: -0.1700

Data Index: 786504 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6683. Min Act: -0.1700

Data Index: 992685 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6527. Min Act: -0.1700

Data Index: 852617 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6683. Min Act: -0.1700

Data Index: 106260 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6683. Min Act: -0.1700

Data Index: 161841 (C4 (Web Text))

Max Activating Token Index: 51

Text #17

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6370. Min Act: -0.1700

Data Index: 437486 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6057. Min Act: -0.1700

Data Index: 967376 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 3.9342. Min Range: -3.9342

Max Act: 3.6057. Min Act: -0.1700

Data Index: 686117 (C4 (Web Text))

Max Activating Token Index: 468