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

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

Neuron 314 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.5651. Min Act: -0.1699

Data Index: 1620871 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.5338. Min Act: -0.1700

Data Index: 195815 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.5025. Min Act: -0.1700

Data Index: 1359460 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.5181. Min Act: -0.1700

Data Index: 348355 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4868. Min Act: -0.1700

Data Index: 867959 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4868. Min Act: -0.1700

Data Index: 383040 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.5025. Min Act: -0.1700

Data Index: 1284699 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4711. Min Act: -0.1700

Data Index: 1261209 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4555. Min Act: -0.1700

Data Index: 88241 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4398. Min Act: -0.1700

Data Index: 1034388 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4555. Min Act: -0.1700

Data Index: 798617 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4241. Min Act: -0.1700

Data Index: 724078 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4084. Min Act: -0.1700

Data Index: 819851 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.3927. Min Act: -0.1700

Data Index: 466776 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4084. Min Act: -0.1700

Data Index: 310104 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.3770. Min Act: -0.1700

Data Index: 631427 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.3770. Min Act: -0.1700

Data Index: 1186171 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.3770. Min Act: -0.1700

Data Index: 606831 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.3927. Min Act: -0.1700

Data Index: 169276 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 3.5651. Min Range: -3.5651

Max Act: 3.4084. Min Act: -0.1700

Data Index: 1204984 (C4 (Web Text))

Max Activating Token Index: 234