Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 350 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.3130. Min Act: -0.1700

Data Index: 1365156 (Python Code)

Max Activating Token Index: 560

Text #1

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.2392. Min Act: -0.1700

Data Index: 200966 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1778. Min Act: -0.1700

Data Index: 698273 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1918. Min Act: -0.1700

Data Index: 1495629 (Python Code)

Max Activating Token Index: 307

Text #4

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1607. Min Act: -0.1700

Data Index: 1640686 (Python Code)

Max Activating Token Index: 729

Text #5

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1558. Min Act: -0.1700

Data Index: 1491562 (Python Code)

Max Activating Token Index: 168

Text #6

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1353. Min Act: -0.1700

Data Index: 1633245 (Python Code)

Max Activating Token Index: 395

Text #7

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1198. Min Act: -0.1700

Data Index: 1563578 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1197. Min Act: -0.1700

Data Index: 1517073 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.1211. Min Act: -0.1700

Data Index: 1521226 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0477. Min Act: -0.1700

Data Index: 1622628 (Python Code)

Max Activating Token Index: 914

Text #11

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0797. Min Act: -0.1700

Data Index: 1636547 (Python Code)

Max Activating Token Index: 462

Text #12

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0386. Min Act: -0.1700

Data Index: 1591773 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0492. Min Act: -0.1700

Data Index: 1343004 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0448. Min Act: -0.1700

Data Index: 1512071 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0572. Min Act: -0.1700

Data Index: 1493434 (Python Code)

Max Activating Token Index: 451

Text #16

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0285. Min Act: -0.1700

Data Index: 1568043 (Python Code)

Max Activating Token Index: 279

Text #17

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0235. Min Act: -0.1700

Data Index: 1486063 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 3.3130. Min Range: -3.3130

Max Act: 3.0039. Min Act: -0.1700

Data Index: 1560303 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 3.3130. Min Range: -3.3130

Max Act: 2.9977. Min Act: -0.1700

Data Index: 1500320 (Python Code)

Max Activating Token Index: 409