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

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

Neuron 1230 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: 8.9893. Min Range: -8.9893

Max Act: 8.9893. Min Act: -0.1700

Data Index: 1180294 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.8643. Min Act: -0.1700

Data Index: 1098770 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.6768. Min Act: -0.1700

Data Index: 2433 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.6768. Min Act: -0.1700

Data Index: 889037 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.6143. Min Act: -0.1700

Data Index: 1000034 (C4 (Web Text))

Max Activating Token Index: 496

Text #5

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.5205. Min Act: -0.1700

Data Index: 627606 (C4 (Web Text))

Max Activating Token Index: 821

Text #6

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.4893. Min Act: -0.1700

Data Index: 750930 (C4 (Web Text))

Max Activating Token Index: 345

Text #7

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.5830. Min Act: -0.1700

Data Index: 20690 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.5830. Min Act: -0.1700

Data Index: 620576 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.3643. Min Act: -0.1700

Data Index: 1074753 (C4 (Web Text))

Max Activating Token Index: 883

Text #10

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.3955. Min Act: -0.1700

Data Index: 237367 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.3643. Min Act: -0.1700

Data Index: 416006 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.4893. Min Act: -0.1700

Data Index: 1093686 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.4893. Min Act: -0.1700

Data Index: 872983 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.5518. Min Act: -0.1700

Data Index: 526661 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.4893. Min Act: -0.1700

Data Index: 384764 (C4 (Web Text))

Max Activating Token Index: 419

Text #16

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.3330. Min Act: -0.1700

Data Index: 1183650 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.3955. Min Act: -0.1700

Data Index: 1252385 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.3018. Min Act: -0.1700

Data Index: 767664 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 8.9893. Min Range: -8.9893

Max Act: 8.1455. Min Act: -0.1700

Data Index: 658931 (C4 (Web Text))

Max Activating Token Index: 407