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

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

Neuron 460 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: 4.4329. Min Range: -4.4329

Max Act: 4.4329. Min Act: -0.1700

Data Index: 966018 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.3704. Min Act: -0.1700

Data Index: 995714 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.3079. Min Act: -0.1700

Data Index: 1084302 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.3079. Min Act: -0.1700

Data Index: 869921 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.2142. Min Act: -0.1700

Data Index: 996669 (C4 (Web Text))

Max Activating Token Index: 118

Text #5

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.2454. Min Act: -0.1700

Data Index: 1085691 (C4 (Web Text))

Max Activating Token Index: 583

Text #6

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.2454. Min Act: -0.1700

Data Index: 656530 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.3392. Min Act: -0.1700

Data Index: 141074 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.2142. Min Act: -0.1700

Data Index: 380380 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.1204. Min Act: -0.1700

Data Index: 693170 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.1829. Min Act: -0.1700

Data Index: 358891 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.1516. Min Act: -0.1700

Data Index: 431879 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.1516. Min Act: -0.1700

Data Index: 148528 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.1516. Min Act: -0.1700

Data Index: 407099 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.0579. Min Act: -0.1700

Data Index: 432681 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.1829. Min Act: -0.1700

Data Index: 824017 (C4 (Web Text))

Max Activating Token Index: 463

Text #16

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.0266. Min Act: -0.1700

Data Index: 859011 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.0579. Min Act: -0.1700

Data Index: 828927 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.0891. Min Act: -0.1700

Data Index: 821985 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 4.4329. Min Range: -4.4329

Max Act: 4.0579. Min Act: -0.1700

Data Index: 247095 (C4 (Web Text))

Max Activating Token Index: 344