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

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

Neuron 1790 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0748. Min Range: -5.0748

Max Act: 5.0748. Min Act: -0.1700

Data Index: 1186346 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.7623. Min Act: -0.1700

Data Index: 51543 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.7310. Min Act: -0.1700

Data Index: 894131 (C4 (Web Text))

Max Activating Token Index: 304

Text #3

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.6998. Min Act: -0.1700

Data Index: 399247 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.4185. Min Act: -0.1700

Data Index: 824038 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.3560. Min Act: -0.1700

Data Index: 758291 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.2622. Min Act: -0.1700

Data Index: 67680 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.1684. Min Act: -0.1700

Data Index: 1630120 (Python Code)

Max Activating Token Index: 193

Text #8

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.0747. Min Act: -0.1700

Data Index: 1570031 (Python Code)

Max Activating Token Index: 408

Text #9

Max Range: 5.0748. Min Range: -5.0748

Max Act: 4.0434. Min Act: -0.1700

Data Index: 37710 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.9496. Min Act: -0.1700

Data Index: 21484 (C4 (Web Text))

Max Activating Token Index: 491

Text #11

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.9496. Min Act: -0.1700

Data Index: 1297491 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.8871. Min Act: -0.1700

Data Index: 1339896 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.8558. Min Act: -0.1700

Data Index: 333913 (C4 (Web Text))

Max Activating Token Index: 842

Text #14

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.8245. Min Act: -0.1700

Data Index: 738335 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.8245. Min Act: -0.1700

Data Index: 985382 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.7463. Min Act: -0.1700

Data Index: 213561 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.7619. Min Act: -0.1700

Data Index: 1002089 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.7307. Min Act: -0.1700

Data Index: 856533 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 5.0748. Min Range: -5.0748

Max Act: 3.6994. Min Act: -0.1700

Data Index: 200316 (C4 (Web Text))

Max Activating Token Index: 839