Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1111 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.0905. Min Range: -4.0905

Max Act: 4.0905. Min Act: -0.1700

Data Index: 576419 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 4.0905. Min Range: -4.0905

Max Act: 4.0749. Min Act: -0.1700

Data Index: 385897 (C4 (Web Text))

Max Activating Token Index: 250

Text #2

Max Range: 4.0905. Min Range: -4.0905

Max Act: 4.0749. Min Act: -0.1700

Data Index: 1550951 (Python Code)

Max Activating Token Index: 403

Text #3

Max Range: 4.0905. Min Range: -4.0905

Max Act: 4.0280. Min Act: -0.1700

Data Index: 816718 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.9811. Min Act: -0.1700

Data Index: 836067 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.9811. Min Act: -0.1700

Data Index: 445902 (C4 (Web Text))

Max Activating Token Index: 893

Text #6

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.9811. Min Act: -0.1700

Data Index: 903974 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8716. Min Act: -0.1700

Data Index: 690220 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.9342. Min Act: -0.1700

Data Index: 713262 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.9185. Min Act: -0.1700

Data Index: 1128798 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8716. Min Act: -0.1700

Data Index: 1247166 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.7465. Min Act: -0.1700

Data Index: 890450 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8716. Min Act: -0.1700

Data Index: 985572 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8716. Min Act: -0.1700

Data Index: 691623 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8403. Min Act: -0.1700

Data Index: 594031 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8403. Min Act: -0.1700

Data Index: 782063 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8872. Min Act: -0.1700

Data Index: 1160349 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.7308. Min Act: -0.1700

Data Index: 352170 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.8560. Min Act: -0.1700

Data Index: 1119700 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 4.0905. Min Range: -4.0905

Max Act: 3.7934. Min Act: -0.1700

Data Index: 1113548 (C4 (Web Text))

Max Activating Token Index: 29