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

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

Neuron 277 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4848. Min Act: -0.1700

Data Index: 851227 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4848. Min Act: -0.1700

Data Index: 262755 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4848. Min Act: -0.1700

Data Index: 600173 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4534. Min Act: -0.1700

Data Index: 440126 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4221. Min Act: -0.1700

Data Index: 1115750 (C4 (Web Text))

Max Activating Token Index: 480

Text #5

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4221. Min Act: -0.1700

Data Index: 1064515 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4221. Min Act: -0.1700

Data Index: 1350652 (C4 (Web Text))

Max Activating Token Index: 454

Text #7

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 137945 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.4221. Min Act: -0.1700

Data Index: 230676 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 626449 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 402499 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 421540 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 515870 (C4 (Web Text))

Max Activating Token Index: 654

Text #13

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 635150 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1004300 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 227506 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 1054631 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 613778 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 346105 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 3.4848. Min Range: -3.4848

Max Act: 3.3907. Min Act: -0.1700

Data Index: 582100 (C4 (Web Text))

Max Activating Token Index: 43