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

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

Neuron 1835 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: 3.7555. Min Range: -3.7555

Max Act: 3.7555. Min Act: -0.1700

Data Index: 1564237 (Python Code)

Max Activating Token Index: 695

Text #1

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6634. Min Act: -0.1700

Data Index: 1436851 (Python Code)

Max Activating Token Index: 878

Text #2

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.7426. Min Act: -0.1700

Data Index: 1362208 (Python Code)

Max Activating Token Index: 946

Text #3

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6302. Min Act: -0.1700

Data Index: 1420266 (Python Code)

Max Activating Token Index: 688

Text #4

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6273. Min Act: -0.1700

Data Index: 846573 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6389. Min Act: -0.1700

Data Index: 1497861 (Python Code)

Max Activating Token Index: 696

Text #6

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5754. Min Act: -0.1700

Data Index: 133176 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.6275. Min Act: -0.1700

Data Index: 1648687 (Python Code)

Max Activating Token Index: 811

Text #8

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5690. Min Act: -0.1700

Data Index: 1416484 (Python Code)

Max Activating Token Index: 490

Text #9

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5453. Min Act: -0.1700

Data Index: 577698 (C4 (Web Text))

Max Activating Token Index: 970

Text #10

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5440. Min Act: -0.1700

Data Index: 834930 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5918. Min Act: -0.1700

Data Index: 1485856 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5587. Min Act: -0.1700

Data Index: 139746 (C4 (Web Text))

Max Activating Token Index: 398

Text #13

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5412. Min Act: -0.1700

Data Index: 1501938 (Python Code)

Max Activating Token Index: 277

Text #14

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5332. Min Act: -0.1700

Data Index: 1475362 (Python Code)

Max Activating Token Index: 199

Text #15

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5413. Min Act: -0.1700

Data Index: 713385 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5008. Min Act: -0.1700

Data Index: 526747 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5450. Min Act: -0.1700

Data Index: 1511205 (Python Code)

Max Activating Token Index: 1015

Text #18

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5228. Min Act: -0.1700

Data Index: 1204375 (C4 (Web Text))

Max Activating Token Index: 1004

Text #19

Max Range: 3.7555. Min Range: -3.7555

Max Act: 3.5031. Min Act: -0.1700

Data Index: 1057292 (C4 (Web Text))

Max Activating Token Index: 770