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

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

Neuron 880 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0662. Min Act: -0.1700

Data Index: 1341451 (C4 (Web Text))

Max Activating Token Index: 741

Text #1

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0350. Min Act: -0.1700

Data Index: 54127 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0037. Min Act: -0.1700

Data Index: 821051 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0037. Min Act: -0.1700

Data Index: 1066577 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0662. Min Act: -0.1700

Data Index: 839845 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0037. Min Act: -0.1700

Data Index: 1082929 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9725. Min Act: -0.1700

Data Index: 1092344 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9412. Min Act: -0.1700

Data Index: 801955 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9725. Min Act: -0.1700

Data Index: 66822 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9725. Min Act: -0.1700

Data Index: 39821 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9725. Min Act: -0.1700

Data Index: 133747 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9725. Min Act: -0.1700

Data Index: 1242269 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9100. Min Act: -0.1700

Data Index: 585550 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9412. Min Act: -0.1700

Data Index: 595927 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9100. Min Act: -0.1700

Data Index: 462747 (C4 (Web Text))

Max Activating Token Index: 243

Text #15

Max Range: 5.0662. Min Range: -5.0662

Max Act: 5.0037. Min Act: -0.1700

Data Index: 1292804 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.9412. Min Act: -0.1700

Data Index: 1233320 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.7850. Min Act: -0.1700

Data Index: 1316023 (C4 (Web Text))

Max Activating Token Index: 442

Text #18

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.8475. Min Act: -0.1700

Data Index: 251254 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 5.0662. Min Range: -5.0662

Max Act: 4.8787. Min Act: -0.1700

Data Index: 730965 (C4 (Web Text))

Max Activating Token Index: 710