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

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

Neuron 1517 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: 3.5848. Min Range: -3.5848

Max Act: 3.5848. Min Act: -0.1700

Data Index: 1078239 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.5535. Min Act: -0.1700

Data Index: 1231750 (C4 (Web Text))

Max Activating Token Index: 417

Text #2

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3967. Min Act: -0.1700

Data Index: 1127807 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3340. Min Act: -0.1700

Data Index: 1354943 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3340. Min Act: -0.1700

Data Index: 496663 (C4 (Web Text))

Max Activating Token Index: 823

Text #5

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3340. Min Act: -0.1700

Data Index: 498089 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3340. Min Act: -0.1700

Data Index: 798608 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3967. Min Act: -0.1700

Data Index: 662897 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.1768. Min Act: -0.1700

Data Index: 982803 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2869. Min Act: -0.1700

Data Index: 1009281 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2869. Min Act: -0.1700

Data Index: 55402 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.3340. Min Act: -0.1700

Data Index: 822125 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2083. Min Act: -0.1700

Data Index: 253640 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2712. Min Act: -0.1700

Data Index: 371464 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2397. Min Act: -0.1700

Data Index: 553720 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1068563 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2240. Min Act: -0.1700

Data Index: 48737 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.2240. Min Act: -0.1700

Data Index: 834659 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.1925. Min Act: -0.1700

Data Index: 1293662 (C4 (Web Text))

Max Activating Token Index: 126

Text #19

Max Range: 3.5848. Min Range: -3.5848

Max Act: 3.1768. Min Act: -0.1700

Data Index: 237690 (C4 (Web Text))

Max Activating Token Index: 906