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

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

Neuron 311 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.5735. Min Act: -0.1700

Data Index: 941424 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.5423. Min Act: -0.1700

Data Index: 1225104 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.5735. Min Act: -0.1700

Data Index: 540732 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.4485. Min Act: -0.1700

Data Index: 878732 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.4798. Min Act: -0.1700

Data Index: 868341 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.4798. Min Act: -0.1700

Data Index: 477851 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.4798. Min Act: -0.1700

Data Index: 241026 (C4 (Web Text))

Max Activating Token Index: 821

Text #7

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.4173. Min Act: -0.1700

Data Index: 1208450 (C4 (Web Text))

Max Activating Token Index: 98

Text #8

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.3860. Min Act: -0.1700

Data Index: 62786 (C4 (Web Text))

Max Activating Token Index: 453

Text #9

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.3860. Min Act: -0.1700

Data Index: 222403 (C4 (Web Text))

Max Activating Token Index: 993

Text #10

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.3860. Min Act: -0.1700

Data Index: 1010836 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2610. Min Act: -0.1700

Data Index: 666237 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2923. Min Act: -0.1700

Data Index: 1061449 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2610. Min Act: -0.1700

Data Index: 805832 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2923. Min Act: -0.1700

Data Index: 725624 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2610. Min Act: -0.1700

Data Index: 780032 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2923. Min Act: -0.1700

Data Index: 269664 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2298. Min Act: -0.1700

Data Index: 1300154 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.2610. Min Act: -0.1700

Data Index: 440635 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 5.5735. Min Range: -5.5735

Max Act: 5.1985. Min Act: -0.1700

Data Index: 8144 (C4 (Web Text))

Max Activating Token Index: 62