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

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

Neuron 1570 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: 4.0635. Min Range: -4.0635

Max Act: 4.0635. Min Act: -0.1691

Data Index: 386458 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 4.0635. Min Range: -4.0635

Max Act: 4.0490. Min Act: -0.1663

Data Index: 260287 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 4.0635. Min Range: -4.0635

Max Act: 4.0492. Min Act: -0.1698

Data Index: 470546 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 4.0635. Min Range: -4.0635

Max Act: 4.0055. Min Act: -0.1700

Data Index: 1228381 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.9758. Min Act: -0.1700

Data Index: 1536699 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.9705. Min Act: -0.1700

Data Index: 1655214 (Python Code)

Max Activating Token Index: 626

Text #6

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.9466. Min Act: -0.1644

Data Index: 133776 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.9517. Min Act: -0.1699

Data Index: 938079 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8904. Min Act: -0.1021

Data Index: 1648566 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8650. Min Act: -0.1699

Data Index: 1636560 (Python Code)

Max Activating Token Index: 239

Text #10

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8362. Min Act: -0.1700

Data Index: 679531 (C4 (Web Text))

Max Activating Token Index: 976

Text #11

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8410. Min Act: -0.1697

Data Index: 1554795 (Python Code)

Max Activating Token Index: 644

Text #12

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8535. Min Act: -0.1696

Data Index: 1531011 (Python Code)

Max Activating Token Index: 71

Text #13

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8497. Min Act: -0.1698

Data Index: 1441640 (Python Code)

Max Activating Token Index: 557

Text #14

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.8289. Min Act: -0.1693

Data Index: 1631688 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.7904. Min Act: -0.1700

Data Index: 1023556 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.7913. Min Act: -0.1663

Data Index: 1522988 (Python Code)

Max Activating Token Index: 597

Text #17

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.7800. Min Act: -0.1700

Data Index: 361461 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.7795. Min Act: -0.1683

Data Index: 1530157 (Python Code)

Max Activating Token Index: 684

Text #19

Max Range: 4.0635. Min Range: -4.0635

Max Act: 3.7619. Min Act: -0.1699

Data Index: 1551337 (Python Code)

Max Activating Token Index: 424