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

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

Neuron 748 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3917. Min Act: -0.1700

Data Index: 1527382 (Python Code)

Max Activating Token Index: 141

Text #1

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3603. Min Act: -0.1700

Data Index: 1653970 (Python Code)

Max Activating Token Index: 543

Text #2

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3603. Min Act: -0.1700

Data Index: 1649489 (Python Code)

Max Activating Token Index: 300

Text #3

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3446. Min Act: -0.1700

Data Index: 1478564 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1556268 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1473686 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1541201 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1602387 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1607154 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1433573 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1502050 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1570823 (Python Code)

Max Activating Token Index: 329

Text #12

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1536739 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2504. Min Act: -0.1700

Data Index: 1639019 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2818. Min Act: -0.1700

Data Index: 1546196 (Python Code)

Max Activating Token Index: 853

Text #15

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1413564 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1580398 (Python Code)

Max Activating Token Index: 568

Text #17

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2818. Min Act: -0.1700

Data Index: 1531544 (Python Code)

Max Activating Token Index: 302

Text #18

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.3132. Min Act: -0.1700

Data Index: 1648911 (Python Code)

Max Activating Token Index: 880

Text #19

Max Range: 3.3917. Min Range: -3.3917

Max Act: 3.2661. Min Act: -0.1700

Data Index: 1555447 (Python Code)

Max Activating Token Index: 713