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

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

Neuron 1762 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.8539. Min Act: -0.1700

Data Index: 979977 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7444. Min Act: -0.1700

Data Index: 1509111 (Python Code)

Max Activating Token Index: 268

Text #2

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1482484 (Python Code)

Max Activating Token Index: 750

Text #3

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1441081 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 298496 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1590319 (Python Code)

Max Activating Token Index: 489

Text #6

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1413063 (Python Code)

Max Activating Token Index: 384

Text #7

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1623412 (Python Code)

Max Activating Token Index: 741

Text #8

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1587399 (Python Code)

Max Activating Token Index: 280

Text #9

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1412154 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1473602 (Python Code)

Max Activating Token Index: 315

Text #11

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6975. Min Act: -0.1700

Data Index: 1529873 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1425662 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1446513 (Python Code)

Max Activating Token Index: 515

Text #14

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6818. Min Act: -0.1700

Data Index: 1142484 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1548296 (Python Code)

Max Activating Token Index: 629

Text #16

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7131. Min Act: -0.1700

Data Index: 1559373 (Python Code)

Max Activating Token Index: 279

Text #17

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6975. Min Act: -0.1700

Data Index: 1586223 (Python Code)

Max Activating Token Index: 645

Text #18

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.6662. Min Act: -0.1700

Data Index: 1485179 (Python Code)

Max Activating Token Index: 192

Text #19

Max Range: 3.8539. Min Range: -3.8539

Max Act: 3.7288. Min Act: -0.1700

Data Index: 1590266 (Python Code)

Max Activating Token Index: 705