Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.3792. Min Act: -0.1700

Data Index: 1337473 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.2542. Min Act: -0.1700

Data Index: 711663 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1917. Min Act: -0.1700

Data Index: 1342111 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1917. Min Act: -0.1700

Data Index: 886194 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1604. Min Act: -0.1700

Data Index: 702434 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1917. Min Act: -0.1700

Data Index: 1048909 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1604. Min Act: -0.1700

Data Index: 481471 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0979. Min Act: -0.1700

Data Index: 827436 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1292. Min Act: -0.1700

Data Index: 334582 (C4 (Web Text))

Max Activating Token Index: 154

Text #9

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1292. Min Act: -0.1700

Data Index: 693650 (C4 (Web Text))

Max Activating Token Index: 36

Text #10

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.1604. Min Act: -0.1700

Data Index: 641048 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 5.3792. Min Range: -5.3792

Max Act: 4.9417. Min Act: -0.1700

Data Index: 1188801 (C4 (Web Text))

Max Activating Token Index: 869

Text #12

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0667. Min Act: -0.1700

Data Index: 972156 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0354. Min Act: -0.1700

Data Index: 1207632 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0667. Min Act: -0.1700

Data Index: 1179968 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0667. Min Act: -0.1700

Data Index: 502347 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0042. Min Act: -0.1700

Data Index: 245909 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0042. Min Act: -0.1700

Data Index: 413489 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0354. Min Act: -0.1700

Data Index: 408543 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 5.3792. Min Range: -5.3792

Max Act: 5.0354. Min Act: -0.1700

Data Index: 190576 (C4 (Web Text))

Max Activating Token Index: 664