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

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

Neuron 929 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: 5.2306. Min Range: -5.2306

Max Act: 5.2306. Min Act: -0.1700

Data Index: 157222 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1993. Min Act: -0.1700

Data Index: 1177437 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1368. Min Act: -0.1700

Data Index: 820889 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0431. Min Act: -0.1700

Data Index: 625259 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1681. Min Act: -0.1700

Data Index: 266872 (C4 (Web Text))

Max Activating Token Index: 270

Text #5

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1681. Min Act: -0.1700

Data Index: 738548 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1368. Min Act: -0.1700

Data Index: 1053640 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1368. Min Act: -0.1700

Data Index: 269740 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1056. Min Act: -0.1700

Data Index: 93359 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1368. Min Act: -0.1700

Data Index: 760013 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1681. Min Act: -0.1700

Data Index: 490841 (C4 (Web Text))

Max Activating Token Index: 235

Text #11

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0743. Min Act: -0.1700

Data Index: 194090 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0743. Min Act: -0.1700

Data Index: 69879 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0431. Min Act: -0.1700

Data Index: 660795 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.1368. Min Act: -0.1700

Data Index: 282515 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 5.2306. Min Range: -5.2306

Max Act: 4.9806. Min Act: -0.1700

Data Index: 1456694 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0118. Min Act: -0.1700

Data Index: 603857 (C4 (Web Text))

Max Activating Token Index: 965

Text #17

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0743. Min Act: -0.1700

Data Index: 325075 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0118. Min Act: -0.1700

Data Index: 1108876 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 5.2306. Min Range: -5.2306

Max Act: 5.0118. Min Act: -0.1700

Data Index: 1158800 (C4 (Web Text))

Max Activating Token Index: 788