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

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

Neuron 360 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: 5.0831. Min Range: -5.0831

Max Act: 5.0831. Min Act: -0.1700

Data Index: 1653629 (Python Code)

Max Activating Token Index: 756

Text #1

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.7186. Min Act: -0.1700

Data Index: 1584577 (Python Code)

Max Activating Token Index: 565

Text #2

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.7527. Min Act: -0.1700

Data Index: 1445506 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.6712. Min Act: -0.1700

Data Index: 1590962 (Python Code)

Max Activating Token Index: 782

Text #4

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5880. Min Act: -0.1700

Data Index: 171524 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.6035. Min Act: -0.1700

Data Index: 1626007 (Python Code)

Max Activating Token Index: 730

Text #6

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.6363. Min Act: -0.1700

Data Index: 1378133 (Python Code)

Max Activating Token Index: 157

Text #7

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.6324. Min Act: -0.1700

Data Index: 1378843 (Python Code)

Max Activating Token Index: 692

Text #8

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5386. Min Act: -0.1700

Data Index: 129481 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5464. Min Act: -0.1700

Data Index: 1568318 (Python Code)

Max Activating Token Index: 1004

Text #10

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5214. Min Act: -0.1700

Data Index: 1448176 (Python Code)

Max Activating Token Index: 487

Text #11

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5571. Min Act: -0.1700

Data Index: 1551635 (Python Code)

Max Activating Token Index: 877

Text #12

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5706. Min Act: -0.1700

Data Index: 1557922 (Python Code)

Max Activating Token Index: 980

Text #13

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5344. Min Act: -0.1699

Data Index: 502379 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.5108. Min Act: -0.1698

Data Index: 1382665 (Python Code)

Max Activating Token Index: 954

Text #15

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.4554. Min Act: -0.1699

Data Index: 1480058 (Python Code)

Max Activating Token Index: 437

Text #16

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.4875. Min Act: -0.1441

Data Index: 1568213 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.4871. Min Act: -0.1700

Data Index: 1363332 (Python Code)

Max Activating Token Index: 513

Text #18

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.4669. Min Act: -0.1700

Data Index: 1550768 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 5.0831. Min Range: -5.0831

Max Act: 4.4702. Min Act: -0.1700

Data Index: 1577858 (Python Code)

Max Activating Token Index: 729