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

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

Neuron 59 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.9246. Min Act: -0.1700

Data Index: 1586764 (Python Code)

Max Activating Token Index: 893

Text #1

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.8933. Min Act: -0.1700

Data Index: 1620774 (Python Code)

Max Activating Token Index: 703

Text #2

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.7682. Min Act: -0.1700

Data Index: 1426800 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.7369. Min Act: -0.1700

Data Index: 1614936 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1652721 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.6743. Min Act: -0.1700

Data Index: 1557837 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1406810 (Python Code)

Max Activating Token Index: 502

Text #7

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.6743. Min Act: -0.1699

Data Index: 1537857 (Python Code)

Max Activating Token Index: 675

Text #8

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.7056. Min Act: -0.1700

Data Index: 1589095 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.6743. Min Act: -0.1700

Data Index: 1594669 (Python Code)

Max Activating Token Index: 988

Text #10

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.6117. Min Act: -0.1699

Data Index: 1426638 (Python Code)

Max Activating Token Index: 445

Text #11

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1370802 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.6117. Min Act: -0.1700

Data Index: 1398646 (Python Code)

Max Activating Token Index: 371

Text #13

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1364915 (Python Code)

Max Activating Token Index: 252

Text #14

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1462692 (Python Code)

Max Activating Token Index: 802

Text #15

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.5804. Min Act: -0.1700

Data Index: 1522695 (Python Code)

Max Activating Token Index: 693

Text #16

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.5804. Min Act: -0.1700

Data Index: 1367781 (Python Code)

Max Activating Token Index: 955

Text #17

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1471486 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.5491. Min Act: -0.1700

Data Index: 1620207 (Python Code)

Max Activating Token Index: 789

Text #19

Max Range: 3.9246. Min Range: -3.9246

Max Act: 3.4864. Min Act: -0.1639

Data Index: 1549365 (Python Code)

Max Activating Token Index: 478