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

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

Neuron 53 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: 4.1649. Min Range: -4.1649

Max Act: 4.1649. Min Act: -0.1700

Data Index: 806676 (C4 (Web Text))

Max Activating Token Index: 120

Text #1

Max Range: 4.1649. Min Range: -4.1649

Max Act: 4.1649. Min Act: -0.1700

Data Index: 764838 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 4.1649. Min Range: -4.1649

Max Act: 4.0242. Min Act: -0.1700

Data Index: 358327 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 4.1649. Min Range: -4.1649

Max Act: 4.0398. Min Act: -0.1700

Data Index: 567382 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.9773. Min Act: -0.1700

Data Index: 694459 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.9617. Min Act: -0.1700

Data Index: 1039593 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.9148. Min Act: -0.1700

Data Index: 466416 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.9304. Min Act: -0.1700

Data Index: 1298672 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.9148. Min Act: -0.1700

Data Index: 1008757 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.9304. Min Act: -0.1700

Data Index: 989647 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8522. Min Act: -0.1700

Data Index: 1300875 (C4 (Web Text))

Max Activating Token Index: 475

Text #11

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8679. Min Act: -0.1700

Data Index: 691078 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8053. Min Act: -0.1700

Data Index: 968889 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8053. Min Act: -0.1700

Data Index: 395393 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8209. Min Act: -0.1700

Data Index: 529421 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.7897. Min Act: -0.1700

Data Index: 495972 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8053. Min Act: -0.1700

Data Index: 1276431 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.7740. Min Act: -0.1700

Data Index: 910082 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.7427. Min Act: -0.1700

Data Index: 577060 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 4.1649. Min Range: -4.1649

Max Act: 3.8053. Min Act: -0.1700

Data Index: 1014465 (C4 (Web Text))

Max Activating Token Index: 762