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

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

Neuron 155 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.8665. Min Act: -0.1700

Data Index: 977140 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.7103. Min Act: -0.1700

Data Index: 1238773 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.6165. Min Act: -0.1700

Data Index: 1205652 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.6165. Min Act: -0.1700

Data Index: 855834 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.6165. Min Act: -0.1700

Data Index: 610710 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.6165. Min Act: -0.1700

Data Index: 374507 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.6478. Min Act: -0.1700

Data Index: 1144456 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5853. Min Act: -0.1700

Data Index: 1077426 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5540. Min Act: -0.1699

Data Index: 760240 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.4603. Min Act: -0.1699

Data Index: 482086 (C4 (Web Text))

Max Activating Token Index: 803

Text #10

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5540. Min Act: -0.1700

Data Index: 811535 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5228. Min Act: -0.1700

Data Index: 1349544 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5540. Min Act: -0.1700

Data Index: 86417 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.4915. Min Act: -0.1700

Data Index: 651814 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.4603. Min Act: -0.1700

Data Index: 973671 (C4 (Web Text))

Max Activating Token Index: 714

Text #15

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.4290. Min Act: -0.1700

Data Index: 420606 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5228. Min Act: -0.1700

Data Index: 914137 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.4603. Min Act: -0.1700

Data Index: 1222739 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5228. Min Act: -0.1700

Data Index: 372961 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.8665. Min Range: -5.8665

Max Act: 5.5540. Min Act: -0.1699

Data Index: 18091 (C4 (Web Text))

Max Activating Token Index: 887