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

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

Neuron 1823 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: 5.4402. Min Range: -5.4402

Max Act: 5.4402. Min Act: -0.1700

Data Index: 1619288 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.3465. Min Act: -0.1700

Data Index: 1563457 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1401943 (Python Code)

Max Activating Token Index: 969

Text #3

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.2527. Min Act: -0.1700

Data Index: 1590709 (Python Code)

Max Activating Token Index: 839

Text #4

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1590. Min Act: -0.1700

Data Index: 1379770 (Python Code)

Max Activating Token Index: 667

Text #5

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1902. Min Act: -0.1700

Data Index: 1457051 (Python Code)

Max Activating Token Index: 50

Text #6

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1633391 (Python Code)

Max Activating Token Index: 668

Text #7

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0965. Min Act: -0.1700

Data Index: 1501575 (Python Code)

Max Activating Token Index: 338

Text #8

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1442059 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1479852 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.1277. Min Act: -0.1700

Data Index: 1639733 (Python Code)

Max Activating Token Index: 920

Text #11

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0965. Min Act: -0.1700

Data Index: 1525706 (Python Code)

Max Activating Token Index: 657

Text #12

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0965. Min Act: -0.1700

Data Index: 1543974 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0340. Min Act: -0.1700

Data Index: 1651102 (Python Code)

Max Activating Token Index: 566

Text #14

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0652. Min Act: -0.1700

Data Index: 1497736 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0340. Min Act: -0.1700

Data Index: 1602675 (Python Code)

Max Activating Token Index: 223

Text #16

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0340. Min Act: -0.1700

Data Index: 1530599 (Python Code)

Max Activating Token Index: 781

Text #17

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0652. Min Act: -0.1700

Data Index: 1411829 (Python Code)

Max Activating Token Index: 491

Text #18

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0027. Min Act: -0.1700

Data Index: 1508017 (Python Code)

Max Activating Token Index: 781

Text #19

Max Range: 5.4402. Min Range: -5.4402

Max Act: 5.0027. Min Act: -0.1700

Data Index: 1484207 (Python Code)

Max Activating Token Index: 299