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

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

Neuron 1574 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: 5.8471. Min Range: -5.8471

Max Act: 5.8471. Min Act: -0.1700

Data Index: 722243 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.7846. Min Act: -0.1700

Data Index: 350999 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.7534. Min Act: -0.1700

Data Index: 557002 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6909. Min Act: -0.1700

Data Index: 1312119 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.7221. Min Act: -0.1700

Data Index: 233452 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6909. Min Act: -0.1700

Data Index: 1180757 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6596. Min Act: -0.1700

Data Index: 197366 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6284. Min Act: -0.1700

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 67

Text #8

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6596. Min Act: -0.1700

Data Index: 645782 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6596. Min Act: -0.1700

Data Index: 852429 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5971. Min Act: -0.1700

Data Index: 995469 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.6284. Min Act: -0.1700

Data Index: 866579 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5659. Min Act: -0.1700

Data Index: 861825 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5659. Min Act: -0.1700

Data Index: 568237 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5659. Min Act: -0.1700

Data Index: 617295 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5346. Min Act: -0.1700

Data Index: 569595 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5346. Min Act: -0.1700

Data Index: 681444 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5346. Min Act: -0.1700

Data Index: 342844 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5346. Min Act: -0.1700

Data Index: 275055 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 5.8471. Min Range: -5.8471

Max Act: 5.5034. Min Act: -0.1700

Data Index: 704472 (C4 (Web Text))

Max Activating Token Index: 698