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

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

Neuron 1704 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: 5.1939. Min Range: -5.1939

Max Act: 5.1939. Min Act: -0.1700

Data Index: 222559 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.1314. Min Act: -0.1700

Data Index: 758351 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.1627. Min Act: -0.1700

Data Index: 752693 (C4 (Web Text))

Max Activating Token Index: 846

Text #3

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.1627. Min Act: -0.1700

Data Index: 786946 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.1314. Min Act: -0.1700

Data Index: 1313931 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.1002. Min Act: -0.1700

Data Index: 818845 (C4 (Web Text))

Max Activating Token Index: 204

Text #6

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0689. Min Act: -0.1700

Data Index: 77159 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 5.1939. Min Range: -5.1939

Max Act: 4.9752. Min Act: -0.1700

Data Index: 790292 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0689. Min Act: -0.1700

Data Index: 1161010 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0377. Min Act: -0.1700

Data Index: 1117690 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.1314. Min Act: -0.1700

Data Index: 1083263 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0377. Min Act: -0.1700

Data Index: 967121 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0064. Min Act: -0.1700

Data Index: 769911 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0689. Min Act: -0.1700

Data Index: 490923 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 5.1939. Min Range: -5.1939

Max Act: 4.9752. Min Act: -0.1700

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 5.1939. Min Range: -5.1939

Max Act: 4.8814. Min Act: -0.1700

Data Index: 778046 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 5.1939. Min Range: -5.1939

Max Act: 4.9752. Min Act: -0.1700

Data Index: 912273 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0377. Min Act: -0.1700

Data Index: 603413 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 5.1939. Min Range: -5.1939

Max Act: 4.9752. Min Act: -0.1700

Data Index: 796491 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 5.1939. Min Range: -5.1939

Max Act: 5.0377. Min Act: -0.1700

Data Index: 440845 (C4 (Web Text))

Max Activating Token Index: 308