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

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

Neuron 909 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.7383. Min Act: -0.1700

Data Index: 84941 (C4 (Web Text))

Max Activating Token Index: 440

Text #1

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.7696. Min Act: -0.1700

Data Index: 524040 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.6758. Min Act: -0.1700

Data Index: 989429 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.6133. Min Act: -0.1700

Data Index: 588299 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.5508. Min Act: -0.1700

Data Index: 794225 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.5508. Min Act: -0.1700

Data Index: 1181883 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.5508. Min Act: -0.1700

Data Index: 637651 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.6133. Min Act: -0.1700

Data Index: 478845 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4883. Min Act: -0.1700

Data Index: 670721 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.5196. Min Act: -0.1700

Data Index: 1147820 (C4 (Web Text))

Max Activating Token Index: 456

Text #10

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4883. Min Act: -0.1700

Data Index: 629453 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4571. Min Act: -0.1700

Data Index: 152441 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4571. Min Act: -0.1700

Data Index: 519863 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4571. Min Act: -0.1700

Data Index: 464053 (C4 (Web Text))

Max Activating Token Index: 606

Text #14

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4883. Min Act: -0.1699

Data Index: 161635 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4883. Min Act: -0.1700

Data Index: 706860 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4571. Min Act: -0.1700

Data Index: 1342626 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4258. Min Act: -0.1700

Data Index: 42736 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4258. Min Act: -0.1700

Data Index: 983704 (C4 (Web Text))

Max Activating Token Index: 597

Text #19

Max Range: 4.7696. Min Range: -4.7696

Max Act: 4.4571. Min Act: -0.1700

Data Index: 48871 (C4 (Web Text))

Max Activating Token Index: 414