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

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

Neuron 886 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: 7.3504. Min Range: -7.3504

Max Act: 7.2879. Min Act: -0.1700

Data Index: 287916 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.3504. Min Act: -0.1700

Data Index: 457857 (C4 (Web Text))

Max Activating Token Index: 45

Text #2

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.2879. Min Act: -0.1700

Data Index: 1069504 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.2410. Min Act: -0.1700

Data Index: 686920 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.1785. Min Act: -0.1700

Data Index: 347906 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.1785. Min Act: -0.1700

Data Index: 530287 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.1004. Min Act: -0.1700

Data Index: 206777 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0691. Min Act: -0.1700

Data Index: 694827 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0848. Min Act: -0.1700

Data Index: 231319 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.1473. Min Act: -0.1700

Data Index: 181807 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.1629. Min Act: -0.1700

Data Index: 1256377 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0691. Min Act: -0.1700

Data Index: 567128 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0848. Min Act: -0.1700

Data Index: 801380 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0691. Min Act: -0.1700

Data Index: 1157179 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0223. Min Act: -0.1700

Data Index: 1281071 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 7.3504. Min Range: -7.3504

Max Act: 6.9910. Min Act: -0.1700

Data Index: 1310429 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 7.3504. Min Range: -7.3504

Max Act: 6.9910. Min Act: -0.1700

Data Index: 222444 (C4 (Web Text))

Max Activating Token Index: 659

Text #17

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0535. Min Act: -0.1700

Data Index: 25853 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 7.3504. Min Range: -7.3504

Max Act: 6.9754. Min Act: -0.1700

Data Index: 1129372 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 7.3504. Min Range: -7.3504

Max Act: 7.0223. Min Act: -0.1700

Data Index: 689538 (C4 (Web Text))

Max Activating Token Index: 514