Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 599 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.8657. Min Act: -0.1700

Data Index: 1190944 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.8187. Min Act: -0.1700

Data Index: 834284 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.7249. Min Act: -0.1700

Data Index: 991908 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.7249. Min Act: -0.1700

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6936. Min Act: -0.1700

Data Index: 258459 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.7249. Min Act: -0.1700

Data Index: 264807 (C4 (Web Text))

Max Activating Token Index: 470

Text #6

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6936. Min Act: -0.1700

Data Index: 402547 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6310. Min Act: -0.1700

Data Index: 915442 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6936. Min Act: -0.1700

Data Index: 623039 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6779. Min Act: -0.1700

Data Index: 152069 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6466. Min Act: -0.1700

Data Index: 624269 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6623. Min Act: -0.1700

Data Index: 496792 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6779. Min Act: -0.1700

Data Index: 238252 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6466. Min Act: -0.1700

Data Index: 609822 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6623. Min Act: -0.1700

Data Index: 1181340 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6779. Min Act: -0.1700

Data Index: 195632 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6466. Min Act: -0.1700

Data Index: 636603 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6310. Min Act: -0.1700

Data Index: 247091 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6310. Min Act: -0.1700

Data Index: 1201443 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.8657. Min Range: -3.8657

Max Act: 3.6623. Min Act: -0.1700

Data Index: 461976 (C4 (Web Text))

Max Activating Token Index: 643