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

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

Neuron 776 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1170987 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.8002. Min Act: -0.1700

Data Index: 631790 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7689. Min Act: -0.1700

Data Index: 1164264 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7376. Min Act: -0.1700

Data Index: 1332173 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7376. Min Act: -0.1700

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7063. Min Act: -0.1700

Data Index: 18966 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6750. Min Act: -0.1700

Data Index: 257666 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.7063. Min Act: -0.1700

Data Index: 1167988 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6750. Min Act: -0.1700

Data Index: 1176181 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6437. Min Act: -0.1700

Data Index: 1031462 (C4 (Web Text))

Max Activating Token Index: 327

Text #10

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6750. Min Act: -0.1700

Data Index: 257327 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6437. Min Act: -0.1700

Data Index: 998850 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6437. Min Act: -0.1700

Data Index: 43515 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6124. Min Act: -0.1700

Data Index: 402889 (C4 (Web Text))

Max Activating Token Index: 581

Text #14

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5811. Min Act: -0.1700

Data Index: 179755 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.5811. Min Act: -0.1700

Data Index: 1139759 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6124. Min Act: -0.1700

Data Index: 365722 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6124. Min Act: -0.1700

Data Index: 1131831 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6124. Min Act: -0.1700

Data Index: 258326 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 3.8002. Min Range: -3.8002

Max Act: 3.6124. Min Act: -0.1700

Data Index: 1128103 (C4 (Web Text))

Max Activating Token Index: 234