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

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

Neuron 353 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: 4.1322. Min Range: -4.1322

Max Act: 4.1288. Min Act: -0.1700

Data Index: 1372466 (Python Code)

Max Activating Token Index: 66

Text #1

Max Range: 4.1322. Min Range: -4.1322

Max Act: 4.1322. Min Act: -0.1700

Data Index: 1621803 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 4.1322. Min Range: -4.1322

Max Act: 4.0971. Min Act: -0.1700

Data Index: 1422042 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 4.1322. Min Range: -4.1322

Max Act: 4.0072. Min Act: -0.1700

Data Index: 1458470 (Python Code)

Max Activating Token Index: 747

Text #4

Max Range: 4.1322. Min Range: -4.1322

Max Act: 4.0093. Min Act: -0.1700

Data Index: 1607937 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 4.1322. Min Range: -4.1322

Max Act: 4.0082. Min Act: -0.1700

Data Index: 1573963 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.9721. Min Act: -0.1700

Data Index: 1364778 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.9431. Min Act: -0.1700

Data Index: 1648492 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.9481. Min Act: -0.1700

Data Index: 1383652 (Python Code)

Max Activating Token Index: 863

Text #9

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.9091. Min Act: -0.1700

Data Index: 1438166 (Python Code)

Max Activating Token Index: 496

Text #10

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.9067. Min Act: -0.1700

Data Index: 1430292 (Python Code)

Max Activating Token Index: 27

Text #11

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8700. Min Act: -0.1700

Data Index: 1529753 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8868. Min Act: -0.1700

Data Index: 1480957 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8661. Min Act: -0.1700

Data Index: 1637965 (Python Code)

Max Activating Token Index: 950

Text #14

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8646. Min Act: -0.1700

Data Index: 1608324 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8599. Min Act: -0.1700

Data Index: 1482078 (Python Code)

Max Activating Token Index: 217

Text #16

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8681. Min Act: -0.1700

Data Index: 1470049 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8539. Min Act: -0.1700

Data Index: 1549642 (Python Code)

Max Activating Token Index: 211

Text #18

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8405. Min Act: -0.1700

Data Index: 1630989 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 4.1322. Min Range: -4.1322

Max Act: 3.8659. Min Act: -0.1700

Data Index: 1460477 (Python Code)

Max Activating Token Index: 732