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

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

Neuron 1666 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: 3.6734. Min Range: -3.6734

Max Act: 3.6734. Min Act: -0.1699

Data Index: 916678 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.6622. Min Act: -0.1642

Data Index: 1386608 (Python Code)

Max Activating Token Index: 772

Text #2

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.6711. Min Act: -0.1657

Data Index: 1632004 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.6540. Min Act: -0.1698

Data Index: 1456639 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.5721. Min Act: -0.1697

Data Index: 1437035 (Python Code)

Max Activating Token Index: 1013

Text #5

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.5693. Min Act: -0.1700

Data Index: 1466440 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.5300. Min Act: -0.1542

Data Index: 1625766 (Python Code)

Max Activating Token Index: 443

Text #7

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.5333. Min Act: -0.1696

Data Index: 1534968 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.5219. Min Act: -0.1694

Data Index: 1577020 (Python Code)

Max Activating Token Index: 1022

Text #9

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.4910. Min Act: -0.1699

Data Index: 1410493 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.4981. Min Act: -0.1699

Data Index: 1526582 (Python Code)

Max Activating Token Index: 973

Text #11

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.4125. Min Act: -0.1691

Data Index: 1632890 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.4105. Min Act: -0.0708

Data Index: 1469282 (Python Code)

Max Activating Token Index: 407

Text #13

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.4382. Min Act: -0.1700

Data Index: 1417516 (Python Code)

Max Activating Token Index: 675

Text #14

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.3944. Min Act: -0.1700

Data Index: 1490907 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.4060. Min Act: -0.1674

Data Index: 1466408 (Python Code)

Max Activating Token Index: 279

Text #16

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.3579. Min Act: -0.1699

Data Index: 274673 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.3620. Min Act: -0.1700

Data Index: 1450118 (Python Code)

Max Activating Token Index: 485

Text #18

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.3500. Min Act: -0.1699

Data Index: 1592524 (Python Code)

Max Activating Token Index: 662

Text #19

Max Range: 3.6734. Min Range: -3.6734

Max Act: 3.3624. Min Act: -0.1699

Data Index: 1398054 (Python Code)

Max Activating Token Index: 411