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

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

Neuron 1311 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1285. Min Range: -3.1285

Max Act: 3.1285. Min Act: -0.1700

Data Index: 732781 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 3.1285. Min Range: -3.1285

Max Act: 3.0812. Min Act: -0.1700

Data Index: 730864 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 3.1285. Min Range: -3.1285

Max Act: 3.0023. Min Act: -0.1700

Data Index: 1268387 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.1285. Min Range: -3.1285

Max Act: 3.0023. Min Act: -0.1700

Data Index: 280952 (C4 (Web Text))

Max Activating Token Index: 151

Text #4

Max Range: 3.1285. Min Range: -3.1285

Max Act: 3.0023. Min Act: -0.1700

Data Index: 1109082 (C4 (Web Text))

Max Activating Token Index: 765

Text #5

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9865. Min Act: -0.1700

Data Index: 1248508 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9865. Min Act: -0.1700

Data Index: 416806 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9548. Min Act: -0.1700

Data Index: 592719 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9707. Min Act: -0.1700

Data Index: 1196792 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9865. Min Act: -0.1700

Data Index: 255199 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9707. Min Act: -0.1700

Data Index: 600301 (C4 (Web Text))

Max Activating Token Index: 279

Text #11

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9548. Min Act: -0.1700

Data Index: 496646 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9707. Min Act: -0.1700

Data Index: 685399 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9548. Min Act: -0.1700

Data Index: 572482 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9390. Min Act: -0.1700

Data Index: 516951 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9073. Min Act: -0.1700

Data Index: 277752 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9390. Min Act: -0.1700

Data Index: 264551 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9231. Min Act: -0.1700

Data Index: 1049625 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9548. Min Act: -0.1700

Data Index: 359079 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 3.1285. Min Range: -3.1285

Max Act: 2.9390. Min Act: -0.1700

Data Index: 1208981 (C4 (Web Text))

Max Activating Token Index: 996