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

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

Neuron 1830 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: 5.2542. Min Range: -5.2542

Max Act: 5.2542. Min Act: -0.1700

Data Index: 507271 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.1917. Min Act: -0.1700

Data Index: 948588 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0667. Min Act: -0.1700

Data Index: 1162182 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.1292. Min Act: -0.1700

Data Index: 1211673 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0979. Min Act: -0.1700

Data Index: 479805 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0979. Min Act: -0.1700

Data Index: 29339 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.1292. Min Act: -0.1700

Data Index: 997908 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 1556869 (Python Code)

Max Activating Token Index: 756

Text #8

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 27051 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 901975 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0667. Min Act: -0.1700

Data Index: 479556 (C4 (Web Text))

Max Activating Token Index: 177

Text #11

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 838181 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 1356848 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 222955 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0042. Min Act: -0.1700

Data Index: 120071 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 5.2542. Min Range: -5.2542

Max Act: 4.9729. Min Act: -0.1700

Data Index: 917202 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0354. Min Act: -0.1700

Data Index: 91890 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0042. Min Act: -0.1700

Data Index: 81431 (C4 (Web Text))

Max Activating Token Index: 308

Text #18

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0667. Min Act: -0.1700

Data Index: 437582 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 5.2542. Min Range: -5.2542

Max Act: 5.0042. Min Act: -0.1700

Data Index: 899871 (C4 (Web Text))

Max Activating Token Index: 832