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

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

Neuron 944 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.3963. Min Act: -0.1700

Data Index: 899505 (C4 (Web Text))

Max Activating Token Index: 575

Text #1

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.4275. Min Act: -0.1700

Data Index: 258050 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.4275. Min Act: -0.1700

Data Index: 163698 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.3963. Min Act: -0.1700

Data Index: 488147 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.2713. Min Act: -0.1700

Data Index: 53931 (C4 (Web Text))

Max Activating Token Index: 514

Text #5

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.2400. Min Act: -0.1700

Data Index: 953371 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.3025. Min Act: -0.1700

Data Index: 225248 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.2400. Min Act: -0.1700

Data Index: 336587 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.2088. Min Act: -0.1700

Data Index: 1039740 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1775. Min Act: -0.1700

Data Index: 1092453 (C4 (Web Text))

Max Activating Token Index: 980

Text #10

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1463. Min Act: -0.1700

Data Index: 704475 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1775. Min Act: -0.1700

Data Index: 1199202 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1775. Min Act: -0.1700

Data Index: 1216594 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1150. Min Act: -0.1700

Data Index: 436778 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1463. Min Act: -0.1693

Data Index: 191342 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1463. Min Act: -0.1700

Data Index: 956027 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1775. Min Act: -0.1700

Data Index: 615590 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.0838. Min Act: -0.1700

Data Index: 1176398 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.1150. Min Act: -0.1700

Data Index: 508442 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 5.4275. Min Range: -5.4275

Max Act: 5.0525. Min Act: -0.1700

Data Index: 494841 (C4 (Web Text))

Max Activating Token Index: 899