Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 401 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.2707. Min Act: -0.1700

Data Index: 12649 (C4 (Web Text))

Max Activating Token Index: 718

Text #1

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1090481 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.1291. Min Act: -0.1700

Data Index: 936561 (C4 (Web Text))

Max Activating Token Index: 315

Text #3

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.1448. Min Act: -0.1700

Data Index: 765947 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0660. Min Act: -0.1700

Data Index: 631185 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0502. Min Act: -0.1700

Data Index: 291742 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0344. Min Act: -0.1700

Data Index: 1083993 (C4 (Web Text))

Max Activating Token Index: 592

Text #7

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0186. Min Act: -0.1700

Data Index: 306573 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9870. Min Act: -0.1700

Data Index: 585601 (C4 (Web Text))

Max Activating Token Index: 549

Text #9

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9712. Min Act: -0.1700

Data Index: 137428 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 3.2707. Min Range: -3.2707

Max Act: 3.0186. Min Act: -0.1700

Data Index: 14695 (C4 (Web Text))

Max Activating Token Index: 810

Text #11

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9870. Min Act: -0.1700

Data Index: 1317159 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9554. Min Act: -0.1700

Data Index: 132666 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9395. Min Act: -0.1700

Data Index: 1197534 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.9078. Min Act: -0.1700

Data Index: 1291336 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.8602. Min Act: -0.1700

Data Index: 1517021 (Python Code)

Max Activating Token Index: 86

Text #16

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.8602. Min Act: -0.1700

Data Index: 863086 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.8602. Min Act: -0.1700

Data Index: 1156417 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.8443. Min Act: -0.1700

Data Index: 391536 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 3.2707. Min Range: -3.2707

Max Act: 2.8284. Min Act: -0.1700

Data Index: 1084268 (C4 (Web Text))

Max Activating Token Index: 867