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

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

Neuron 1734 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: 5.6533. Min Range: -5.6533

Max Act: 5.6533. Min Act: -0.1700

Data Index: 587865 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.4345. Min Act: -0.1700

Data Index: 1340347 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.4658. Min Act: -0.1700

Data Index: 91442 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.4345. Min Act: -0.1700

Data Index: 32063 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.4658. Min Act: -0.1700

Data Index: 1066272 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.4033. Min Act: -0.1700

Data Index: 977522 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.3408. Min Act: -0.1700

Data Index: 880647 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.4345. Min Act: -0.1700

Data Index: 110005 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.3408. Min Act: -0.1700

Data Index: 319414 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.1845. Min Act: -0.1700

Data Index: 596358 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.2158. Min Act: -0.1700

Data Index: 452371 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.2158. Min Act: -0.1700

Data Index: 965095 (C4 (Web Text))

Max Activating Token Index: 420

Text #12

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.1845. Min Act: -0.1700

Data Index: 986649 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.1845. Min Act: -0.1700

Data Index: 648481 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.1220. Min Act: -0.1700

Data Index: 707397 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.1220. Min Act: -0.1700

Data Index: 790392 (C4 (Web Text))

Max Activating Token Index: 180

Text #16

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.0907. Min Act: -0.1700

Data Index: 1348279 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.0907. Min Act: -0.1700

Data Index: 1072636 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.0907. Min Act: -0.1700

Data Index: 45942 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 5.6533. Min Range: -5.6533

Max Act: 5.0595. Min Act: -0.1700

Data Index: 717821 (C4 (Web Text))

Max Activating Token Index: 342