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

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

Neuron 949 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: 5.5349. Min Range: -5.5349

Max Act: 5.5349. Min Act: -0.1700

Data Index: 725982 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 5.5349. Min Range: -5.5349

Max Act: 5.4411. Min Act: -0.1699

Data Index: 322363 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 5.5349. Min Range: -5.5349

Max Act: 5.1911. Min Act: -0.1700

Data Index: 552778 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 5.5349. Min Range: -5.5349

Max Act: 5.2224. Min Act: -0.1700

Data Index: 175828 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 5.5349. Min Range: -5.5349

Max Act: 5.0036. Min Act: -0.1700

Data Index: 1269130 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9724. Min Act: -0.1700

Data Index: 1277016 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9724. Min Act: -0.1700

Data Index: 1000733 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9724. Min Act: -0.1700

Data Index: 1304218 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9411. Min Act: -0.1700

Data Index: 1585691 (Python Code)

Max Activating Token Index: 904

Text #9

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9411. Min Act: -0.1700

Data Index: 316921 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 5.5349. Min Range: -5.5349

Max Act: 5.0036. Min Act: -0.1700

Data Index: 60 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9099. Min Act: -0.1700

Data Index: 1015748 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9411. Min Act: -0.1700

Data Index: 1253614 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.8786. Min Act: -0.1689

Data Index: 789936 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.8786. Min Act: -0.1700

Data Index: 579714 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.9099. Min Act: -0.1700

Data Index: 236167 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.8786. Min Act: -0.1700

Data Index: 173167 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.8786. Min Act: -0.1700

Data Index: 512005 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.8786. Min Act: -0.1700

Data Index: 701122 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 5.5349. Min Range: -5.5349

Max Act: 4.8474. Min Act: -0.1700

Data Index: 1062510 (C4 (Web Text))

Max Activating Token Index: 870