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

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

Neuron 491 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: 6.1936. Min Range: -6.1936

Max Act: 6.1936. Min Act: -0.1700

Data Index: 1234848 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 6.1936. Min Range: -6.1936

Max Act: 6.0530. Min Act: -0.1700

Data Index: 216154 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.9436. Min Act: -0.1700

Data Index: 1514443 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.9436. Min Act: -0.1700

Data Index: 566702 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.9280. Min Act: -0.1700

Data Index: 395009 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8967. Min Act: -0.1700

Data Index: 565106 (C4 (Web Text))

Max Activating Token Index: 552

Text #6

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.9124. Min Act: -0.1700

Data Index: 1581149 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8030. Min Act: -0.1700

Data Index: 926502 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8655. Min Act: -0.1700

Data Index: 295824 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8499. Min Act: -0.1700

Data Index: 585820 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8186. Min Act: -0.1700

Data Index: 699535 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8030. Min Act: -0.1700

Data Index: 1364285 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7405. Min Act: -0.1700

Data Index: 821902 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7561. Min Act: -0.1700

Data Index: 1482033 (Python Code)

Max Activating Token Index: 310

Text #14

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7561. Min Act: -0.1700

Data Index: 585954 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7405. Min Act: -0.1700

Data Index: 1037019 (C4 (Web Text))

Max Activating Token Index: 874

Text #16

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7561. Min Act: -0.1700

Data Index: 421617 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7405. Min Act: -0.1700

Data Index: 501762 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.7874. Min Act: -0.1700

Data Index: 712265 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 6.1936. Min Range: -6.1936

Max Act: 5.8030. Min Act: -0.1700

Data Index: 1654774 (Python Code)

Max Activating Token Index: 1023