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

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

Neuron 2011 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: 3.5843. Min Range: -3.5843

Max Act: 3.5770. Min Act: -0.1700

Data Index: 166763 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.5843. Min Act: -0.1700

Data Index: 595007 (C4 (Web Text))

Max Activating Token Index: 1010

Text #2

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.5517. Min Act: -0.1700

Data Index: 309689 (C4 (Web Text))

Max Activating Token Index: 916

Text #3

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.4447. Min Act: -0.1700

Data Index: 249374 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3899. Min Act: -0.1700

Data Index: 1460065 (Python Code)

Max Activating Token Index: 689

Text #5

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3973. Min Act: -0.1699

Data Index: 401507 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3751. Min Act: -0.1700

Data Index: 1255693 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3620. Min Act: -0.1700

Data Index: 755974 (C4 (Web Text))

Max Activating Token Index: 356

Text #8

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3789. Min Act: -0.1696

Data Index: 1380970 (Python Code)

Max Activating Token Index: 657

Text #9

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.3343. Min Act: -0.1482

Data Index: 915031 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2856. Min Act: -0.1700

Data Index: 545577 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2517. Min Act: -0.1700

Data Index: 1656685 (Python Code)

Max Activating Token Index: 322

Text #12

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2488. Min Act: -0.1699

Data Index: 858600 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2521. Min Act: -0.1700

Data Index: 788088 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2477. Min Act: -0.1700

Data Index: 869516 (C4 (Web Text))

Max Activating Token Index: 565

Text #15

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2264. Min Act: -0.1023

Data Index: 1132566 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2208. Min Act: -0.1700

Data Index: 163817 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2280. Min Act: -0.1700

Data Index: 1087657 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2386. Min Act: -0.1691

Data Index: 527551 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 3.5843. Min Range: -3.5843

Max Act: 3.2484. Min Act: -0.1699

Data Index: 720657 (C4 (Web Text))

Max Activating Token Index: 678