Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 810 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9367. Min Act: -0.1700

Data Index: 1253496 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9054. Min Act: -0.1700

Data Index: 270778 (C4 (Web Text))

Max Activating Token Index: 806

Text #2

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9054. Min Act: -0.1700

Data Index: 348325 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9367. Min Act: -0.1700

Data Index: 924633 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9054. Min Act: -0.1700

Data Index: 976006 (C4 (Web Text))

Max Activating Token Index: 425

Text #5

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.9054. Min Act: -0.1700

Data Index: 49820 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8742. Min Act: -0.1700

Data Index: 1181568 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8742. Min Act: -0.1700

Data Index: 687530 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8742. Min Act: -0.1700

Data Index: 642654 (C4 (Web Text))

Max Activating Token Index: 386

Text #9

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 888847 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8429. Min Act: -0.1700

Data Index: 459345 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 959494 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 313451 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 1168748 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.8116. Min Act: -0.1700

Data Index: 496000 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7490. Min Act: -0.1700

Data Index: 629765 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7803. Min Act: -0.1700

Data Index: 214065 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7490. Min Act: -0.1700

Data Index: 1150480 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7803. Min Act: -0.1700

Data Index: 984374 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 3.9367. Min Range: -3.9367

Max Act: 3.7803. Min Act: -0.1700

Data Index: 1254064 (C4 (Web Text))

Max Activating Token Index: 670