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

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

Neuron 776 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: 7.9914. Min Range: -7.9914

Max Act: 7.9914. Min Act: -0.1700

Data Index: 735019 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.8664. Min Act: -0.1700

Data Index: 1258482 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.8664. Min Act: -0.1700

Data Index: 489308 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4914. Min Act: -0.1700

Data Index: 1153646 (C4 (Web Text))

Max Activating Token Index: 256

Text #4

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4914. Min Act: -0.1700

Data Index: 798206 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4914. Min Act: -0.1700

Data Index: 729961 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4289. Min Act: -0.1700

Data Index: 474988 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4289. Min Act: -0.1700

Data Index: 553347 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3664. Min Act: -0.1700

Data Index: 1373108 (Python Code)

Max Activating Token Index: 986

Text #9

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3664. Min Act: -0.1700

Data Index: 1301585 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3664. Min Act: -0.1700

Data Index: 1310028 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4289. Min Act: -0.1700

Data Index: 953066 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4289. Min Act: -0.1700

Data Index: 563173 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4289. Min Act: -0.1700

Data Index: 574143 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.4914. Min Act: -0.1700

Data Index: 1329521 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3664. Min Act: -0.1700

Data Index: 211840 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3039. Min Act: -0.1700

Data Index: 904962 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3039. Min Act: -0.1700

Data Index: 86170 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3664. Min Act: -0.1700

Data Index: 911379 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 7.9914. Min Range: -7.9914

Max Act: 7.3039. Min Act: -0.1700

Data Index: 429106 (C4 (Web Text))

Max Activating Token Index: 96