Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1333 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.4433. Min Act: -0.1700

Data Index: 183575 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.3183. Min Act: -0.1700

Data Index: 781515 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2871. Min Act: -0.1700

Data Index: 457063 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2871. Min Act: -0.1700

Data Index: 5347 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2558. Min Act: -0.1700

Data Index: 349217 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2558. Min Act: -0.1700

Data Index: 1265541 (C4 (Web Text))

Max Activating Token Index: 409

Text #6

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.3183. Min Act: -0.1700

Data Index: 498249 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1933. Min Act: -0.1700

Data Index: 321974 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2246. Min Act: -0.1700

Data Index: 1219453 (C4 (Web Text))

Max Activating Token Index: 545

Text #9

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2246. Min Act: -0.1700

Data Index: 135727 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1933. Min Act: -0.1700

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2246. Min Act: -0.1700

Data Index: 896852 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1933. Min Act: -0.1700

Data Index: 1296595 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1933. Min Act: -0.1700

Data Index: 599110 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1621. Min Act: -0.1700

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2246. Min Act: -0.1700

Data Index: 1133029 (C4 (Web Text))

Max Activating Token Index: 613

Text #16

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2246. Min Act: -0.1700

Data Index: 248640 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1933. Min Act: -0.1700

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.1933. Min Act: -0.1700

Data Index: 883038 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 5.4433. Min Range: -5.4433

Max Act: 5.2246. Min Act: -0.1700

Data Index: 469774 (C4 (Web Text))

Max Activating Token Index: 978