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

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

Neuron 1254 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: 3.0642. Min Range: -3.0642

Max Act: 3.0589. Min Act: -0.1700

Data Index: 1151274 (C4 (Web Text))

Max Activating Token Index: 944

Text #1

Max Range: 3.0642. Min Range: -3.0642

Max Act: 3.0642. Min Act: -0.1700

Data Index: 1605518 (Python Code)

Max Activating Token Index: 605

Text #2

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.9714. Min Act: -0.1700

Data Index: 1473495 (Python Code)

Max Activating Token Index: 544

Text #3

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.9419. Min Act: -0.1700

Data Index: 847219 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.9420. Min Act: -0.1699

Data Index: 1448979 (Python Code)

Max Activating Token Index: 293

Text #5

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.9398. Min Act: -0.1700

Data Index: 1522044 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8644. Min Act: -0.1700

Data Index: 1472981 (Python Code)

Max Activating Token Index: 347

Text #7

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8521. Min Act: -0.1700

Data Index: 1525046 (Python Code)

Max Activating Token Index: 550

Text #8

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8366. Min Act: -0.1700

Data Index: 782791 (C4 (Web Text))

Max Activating Token Index: 807

Text #9

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8586. Min Act: -0.1700

Data Index: 534389 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8241. Min Act: -0.1700

Data Index: 1574944 (Python Code)

Max Activating Token Index: 151

Text #11

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8350. Min Act: -0.1700

Data Index: 211551 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8009. Min Act: -0.1700

Data Index: 1648738 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8212. Min Act: -0.1455

Data Index: 1460118 (Python Code)

Max Activating Token Index: 100

Text #14

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8167. Min Act: -0.1700

Data Index: 74014 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7964. Min Act: -0.1700

Data Index: 787851 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8015. Min Act: -0.1700

Data Index: 1520391 (Python Code)

Max Activating Token Index: 542

Text #17

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7903. Min Act: -0.1700

Data Index: 1507683 (Python Code)

Max Activating Token Index: 549

Text #18

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.8031. Min Act: -0.1698

Data Index: 1597465 (Python Code)

Max Activating Token Index: 969

Text #19

Max Range: 3.0642. Min Range: -3.0642

Max Act: 2.7985. Min Act: -0.1699

Data Index: 1616331 (Python Code)

Max Activating Token Index: 96