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

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

Neuron 53 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: 3.9021. Min Range: -3.9021

Max Act: 3.9021. Min Act: -0.1700

Data Index: 692437 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.8336. Min Act: -0.1700

Data Index: 897622 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.7355. Min Act: -0.1698

Data Index: 395641 (C4 (Web Text))

Max Activating Token Index: 306

Text #3

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5749. Min Act: -0.1699

Data Index: 910846 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5470. Min Act: -0.1697

Data Index: 640367 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5171. Min Act: -0.1700

Data Index: 470347 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.5047. Min Act: -0.1700

Data Index: 895982 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.4707. Min Act: -0.1700

Data Index: 405338 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3933. Min Act: -0.1699

Data Index: 1639063 (Python Code)

Max Activating Token Index: 1018

Text #9

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3777. Min Act: -0.1699

Data Index: 1391739 (Python Code)

Max Activating Token Index: 578

Text #10

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3943. Min Act: -0.1564

Data Index: 257579 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3488. Min Act: -0.1553

Data Index: 1092891 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3485. Min Act: -0.1698

Data Index: 1624301 (Python Code)

Max Activating Token Index: 218

Text #13

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3593. Min Act: -0.1698

Data Index: 1463164 (Python Code)

Max Activating Token Index: 809

Text #14

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3523. Min Act: -0.1693

Data Index: 1394680 (Python Code)

Max Activating Token Index: 314

Text #15

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3427. Min Act: -0.1699

Data Index: 38737 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3421. Min Act: -0.1662

Data Index: 1582783 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3449. Min Act: -0.1700

Data Index: 1576625 (Python Code)

Max Activating Token Index: 732

Text #18

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3291. Min Act: -0.1700

Data Index: 1591483 (Python Code)

Max Activating Token Index: 547

Text #19

Max Range: 3.9021. Min Range: -3.9021

Max Act: 3.3534. Min Act: -0.1700

Data Index: 1387992 (Python Code)

Max Activating Token Index: 548