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

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

Neuron 38 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: 3.5639. Min Range: -3.5639

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1164430 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.4506. Min Act: -0.1700

Data Index: 375603 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.4758. Min Act: -0.1700

Data Index: 292039 (C4 (Web Text))

Max Activating Token Index: 746

Text #3

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.4564. Min Act: -0.1700

Data Index: 155624 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3999. Min Act: -0.1700

Data Index: 1055561 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3736. Min Act: -0.1700

Data Index: 413078 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3607. Min Act: -0.1700

Data Index: 746982 (C4 (Web Text))

Max Activating Token Index: 414

Text #7

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3795. Min Act: -0.1700

Data Index: 1228685 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.4086. Min Act: -0.1700

Data Index: 1075067 (C4 (Web Text))

Max Activating Token Index: 353

Text #9

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3673. Min Act: -0.1700

Data Index: 443911 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3573. Min Act: -0.1700

Data Index: 942257 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3482. Min Act: -0.1700

Data Index: 1078287 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3718. Min Act: -0.1700

Data Index: 412786 (C4 (Web Text))

Max Activating Token Index: 1005

Text #13

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3637. Min Act: -0.1700

Data Index: 566410 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3663. Min Act: -0.1700

Data Index: 679752 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3684. Min Act: -0.1700

Data Index: 581229 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3283. Min Act: -0.1700

Data Index: 178432 (C4 (Web Text))

Max Activating Token Index: 1000

Text #17

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3474. Min Act: -0.1700

Data Index: 869873 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3436. Min Act: -0.1700

Data Index: 472500 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 3.5639. Min Range: -3.5639

Max Act: 3.3243. Min Act: -0.1700

Data Index: 601023 (C4 (Web Text))

Max Activating Token Index: 172