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

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

Neuron 1484 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: 3.9896. Min Range: -3.9896

Max Act: 3.9896. Min Act: -0.1700

Data Index: 1050815 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.9270. Min Act: -0.1700

Data Index: 9637 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8645. Min Act: -0.1700

Data Index: 1644605 (Python Code)

Max Activating Token Index: 629

Text #3

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1629835 (Python Code)

Max Activating Token Index: 867

Text #4

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1456481 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8958. Min Act: -0.1700

Data Index: 1649524 (Python Code)

Max Activating Token Index: 330

Text #6

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8019. Min Act: -0.1700

Data Index: 1509922 (Python Code)

Max Activating Token Index: 778

Text #7

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8332. Min Act: -0.1700

Data Index: 1554063 (Python Code)

Max Activating Token Index: 155

Text #8

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8645. Min Act: -0.1700

Data Index: 1478068 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.9270. Min Act: -0.1700

Data Index: 1400100 (Python Code)

Max Activating Token Index: 519

Text #10

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8645. Min Act: -0.1700

Data Index: 1454432 (Python Code)

Max Activating Token Index: 631

Text #11

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7707. Min Act: -0.1700

Data Index: 1460044 (Python Code)

Max Activating Token Index: 758

Text #12

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8019. Min Act: -0.1700

Data Index: 1602794 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8332. Min Act: -0.1700

Data Index: 1491501 (Python Code)

Max Activating Token Index: 412

Text #14

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8019. Min Act: -0.1700

Data Index: 1133451 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8332. Min Act: -0.1700

Data Index: 1413702 (Python Code)

Max Activating Token Index: 714

Text #16

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.8019. Min Act: -0.1700

Data Index: 1601611 (Python Code)

Max Activating Token Index: 415

Text #17

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7707. Min Act: -0.1700

Data Index: 1589034 (Python Code)

Max Activating Token Index: 656

Text #18

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7707. Min Act: -0.1700

Data Index: 1408161 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 3.9896. Min Range: -3.9896

Max Act: 3.7394. Min Act: -0.1700

Data Index: 1607033 (Python Code)

Max Activating Token Index: 966