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

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

Neuron 1643 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: 4.0600. Min Range: -4.0600

Max Act: 4.0600. Min Act: -0.1696

Data Index: 1038943 (C4 (Web Text))

Max Activating Token Index: 227

Text #1

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.9975. Min Act: -0.1700

Data Index: 1644649 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8724. Min Act: -0.1689

Data Index: 1535211 (Python Code)

Max Activating Token Index: 470

Text #3

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8411. Min Act: -0.1689

Data Index: 1648047 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8099. Min Act: -0.1699

Data Index: 789602 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8099. Min Act: -0.1700

Data Index: 1526134 (Python Code)

Max Activating Token Index: 257

Text #6

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8099. Min Act: -0.1700

Data Index: 1558166 (Python Code)

Max Activating Token Index: 361

Text #7

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8099. Min Act: -0.1697

Data Index: 1572978 (Python Code)

Max Activating Token Index: 288

Text #8

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8099. Min Act: -0.1698

Data Index: 1124562 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7786. Min Act: -0.1700

Data Index: 1619454 (Python Code)

Max Activating Token Index: 181

Text #10

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7786. Min Act: -0.1700

Data Index: 1611834 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.8099. Min Act: -0.1700

Data Index: 849824 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7473. Min Act: -0.1689

Data Index: 1505539 (Python Code)

Max Activating Token Index: 910

Text #13

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7473. Min Act: -0.1697

Data Index: 1650157 (Python Code)

Max Activating Token Index: 863

Text #14

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7473. Min Act: -0.1699

Data Index: 1540423 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7160. Min Act: -0.1700

Data Index: 1012604 (C4 (Web Text))

Max Activating Token Index: 249

Text #16

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7473. Min Act: -0.1700

Data Index: 383280 (C4 (Web Text))

Max Activating Token Index: 504

Text #17

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7160. Min Act: -0.1700

Data Index: 1455873 (Python Code)

Max Activating Token Index: 846

Text #18

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.7473. Min Act: -0.1700

Data Index: 1399225 (Python Code)

Max Activating Token Index: 414

Text #19

Max Range: 4.0600. Min Range: -4.0600

Max Act: 3.6847. Min Act: -0.1700

Data Index: 1609523 (Python Code)

Max Activating Token Index: 796