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

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

Neuron 1085 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1073. Min Range: -3.1073

Max Act: 3.1073. Min Act: -0.1700

Data Index: 1392421 (Python Code)

Max Activating Token Index: 617

Text #1

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.9651. Min Act: -0.1700

Data Index: 240262 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.9334. Min Act: -0.1700

Data Index: 1359269 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.9176. Min Act: -0.1700

Data Index: 1207163 (C4 (Web Text))

Max Activating Token Index: 456

Text #4

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8700. Min Act: -0.1700

Data Index: 1249673 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 667382 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 104904 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 795244 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 946101 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 277750 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 605529 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 520542 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 513765 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 1167182 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 761412 (C4 (Web Text))

Max Activating Token Index: 3

Text #15

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 1000159 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 955328 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8382. Min Act: -0.1700

Data Index: 915996 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8223. Min Act: -0.1700

Data Index: 933162 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 3.1073. Min Range: -3.1073

Max Act: 2.8223. Min Act: -0.1700

Data Index: 669119 (C4 (Web Text))

Max Activating Token Index: 154