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

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

Neuron 799 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: 3.3274. Min Range: -3.3274

Max Act: 3.3274. Min Act: -0.1700

Data Index: 456160 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2960. Min Act: -0.1700

Data Index: 1180510 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2803. Min Act: -0.1700

Data Index: 1114912 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2332. Min Act: -0.1700

Data Index: 1118744 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2174. Min Act: -0.1700

Data Index: 9466 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2332. Min Act: -0.1700

Data Index: 696152 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2332. Min Act: -0.1700

Data Index: 888740 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2489. Min Act: -0.1700

Data Index: 113957 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2332. Min Act: -0.1700

Data Index: 315394 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1860. Min Act: -0.1700

Data Index: 660518 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2017. Min Act: -0.1700

Data Index: 458687 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.2332. Min Act: -0.1700

Data Index: 765222 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1702. Min Act: -0.1700

Data Index: 936860 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1702. Min Act: -0.1700

Data Index: 863753 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1860. Min Act: -0.1700

Data Index: 147696 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1702. Min Act: -0.1700

Data Index: 296189 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1860. Min Act: -0.1700

Data Index: 214421 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1545. Min Act: -0.1700

Data Index: 711123 (C4 (Web Text))

Max Activating Token Index: 378

Text #18

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1860. Min Act: -0.1700

Data Index: 1049925 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 3.3274. Min Range: -3.3274

Max Act: 3.1387. Min Act: -0.1700

Data Index: 462702 (C4 (Web Text))

Max Activating Token Index: 912