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

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

Neuron 669 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: 3.2664. Min Range: -3.2664

Max Act: 3.2664. Min Act: -0.1700

Data Index: 1246576 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.2193. Min Act: -0.1700

Data Index: 1178924 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1878. Min Act: -0.1700

Data Index: 888247 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1878. Min Act: -0.1700

Data Index: 1217738 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1721. Min Act: -0.1700

Data Index: 41798 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1406. Min Act: -0.1700

Data Index: 496597 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1406. Min Act: -0.1700

Data Index: 451437 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1563. Min Act: -0.1700

Data Index: 378424 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1563. Min Act: -0.1700

Data Index: 199929 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1563. Min Act: -0.1700

Data Index: 789797 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1248. Min Act: -0.1700

Data Index: 820634 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1090. Min Act: -0.1700

Data Index: 882017 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1248. Min Act: -0.1700

Data Index: 417354 (C4 (Web Text))

Max Activating Token Index: 544

Text #13

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1248. Min Act: -0.1700

Data Index: 110388 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.0933. Min Act: -0.1700

Data Index: 305034 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.0933. Min Act: -0.1700

Data Index: 586939 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.0933. Min Act: -0.1700

Data Index: 1188266 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1248. Min Act: -0.1700

Data Index: 308529 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.1090. Min Act: -0.1700

Data Index: 652447 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 3.2664. Min Range: -3.2664

Max Act: 3.0775. Min Act: -0.1700

Data Index: 734142 (C4 (Web Text))

Max Activating Token Index: 436