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

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

Neuron 636 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: 3.1471. Min Range: -3.1471

Max Act: 3.1471. Min Act: -0.1700

Data Index: 1273167 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1471. Min Act: -0.1700

Data Index: 264946 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1156. Min Act: -0.1700

Data Index: 712855 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1314. Min Act: -0.1700

Data Index: 635408 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1156. Min Act: -0.1700

Data Index: 330726 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1156. Min Act: -0.1700

Data Index: 212813 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0998. Min Act: -0.1700

Data Index: 189401 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1156. Min Act: -0.1700

Data Index: 1082369 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1156. Min Act: -0.1700

Data Index: 85922 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0683. Min Act: -0.1700

Data Index: 1259865 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0683. Min Act: -0.1700

Data Index: 318379 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0841. Min Act: -0.1700

Data Index: 1352587 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0841. Min Act: -0.1700

Data Index: 1314365 (C4 (Web Text))

Max Activating Token Index: 588

Text #13

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0683. Min Act: -0.1700

Data Index: 301624 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0998. Min Act: -0.1700

Data Index: 192084 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0525. Min Act: -0.1700

Data Index: 968557 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1314. Min Act: -0.1700

Data Index: 1239536 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.1314. Min Act: -0.1700

Data Index: 370439 (C4 (Web Text))

Max Activating Token Index: 488

Text #18

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0841. Min Act: -0.1700

Data Index: 531725 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 3.1471. Min Range: -3.1471

Max Act: 3.0841. Min Act: -0.1700

Data Index: 1132281 (C4 (Web Text))

Max Activating Token Index: 700