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

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

Neuron 1742 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.7837. Min Act: -0.1700

Data Index: 334456 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.7837. Min Act: -0.1700

Data Index: 1219350 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.7211. Min Act: -0.1700

Data Index: 585054 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6585. Min Act: -0.1700

Data Index: 1082477 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.7211. Min Act: -0.1700

Data Index: 582126 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6898. Min Act: -0.1700

Data Index: 557838 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.7211. Min Act: -0.1700

Data Index: 1266429 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6272. Min Act: -0.1700

Data Index: 682384 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6898. Min Act: -0.1700

Data Index: 1281117 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1112938 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6585. Min Act: -0.1700

Data Index: 767612 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6272. Min Act: -0.1700

Data Index: 221788 (C4 (Web Text))

Max Activating Token Index: 487

Text #12

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6585. Min Act: -0.1700

Data Index: 403334 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5959. Min Act: -0.1700

Data Index: 1053707 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5959. Min Act: -0.1700

Data Index: 251825 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6585. Min Act: -0.1700

Data Index: 281812 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5959. Min Act: -0.1700

Data Index: 60351 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6272. Min Act: -0.1700

Data Index: 214422 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.5959. Min Act: -0.1700

Data Index: 937599 (C4 (Web Text))

Max Activating Token Index: 604

Text #19

Max Range: 3.7837. Min Range: -3.7837

Max Act: 3.6272. Min Act: -0.1700

Data Index: 1037052 (C4 (Web Text))

Max Activating Token Index: 682