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

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

Neuron 1186 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: 5.1467. Min Range: -5.1467

Max Act: 5.1467. Min Act: -0.1700

Data Index: 753521 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 5.1467. Min Range: -5.1467

Max Act: 5.1467. Min Act: -0.1700

Data Index: 1524110 (Python Code)

Max Activating Token Index: 802

Text #2

Max Range: 5.1467. Min Range: -5.1467

Max Act: 5.0842. Min Act: -0.1700

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 5.1467. Min Range: -5.1467

Max Act: 5.0529. Min Act: -0.1700

Data Index: 1578346 (Python Code)

Max Activating Token Index: 343

Text #4

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9904. Min Act: -0.1700

Data Index: 1240000 (C4 (Web Text))

Max Activating Token Index: 507

Text #5

Max Range: 5.1467. Min Range: -5.1467

Max Act: 5.0217. Min Act: -0.1700

Data Index: 918867 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9592. Min Act: -0.1700

Data Index: 519519 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9904. Min Act: -0.1700

Data Index: 236664 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9279. Min Act: -0.1700

Data Index: 578639 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9592. Min Act: -0.1700

Data Index: 363763 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9592. Min Act: -0.1700

Data Index: 1079251 (C4 (Web Text))

Max Activating Token Index: 561

Text #11

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9279. Min Act: -0.1700

Data Index: 105778 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9904. Min Act: -0.1700

Data Index: 386023 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9279. Min Act: -0.1700

Data Index: 463313 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9904. Min Act: -0.1700

Data Index: 991503 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9279. Min Act: -0.1700

Data Index: 970388 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.8967. Min Act: -0.1700

Data Index: 1174959 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9904. Min Act: -0.1700

Data Index: 1155537 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9279. Min Act: -0.1700

Data Index: 223344 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 5.1467. Min Range: -5.1467

Max Act: 4.9279. Min Act: -0.1700

Data Index: 1060918 (C4 (Web Text))

Max Activating Token Index: 381