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

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

Neuron 734 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.7762. Min Act: -0.1700

Data Index: 651588 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.6197. Min Act: -0.1700

Data Index: 1359111 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.5258. Min Act: -0.1700

Data Index: 296107 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.5101. Min Act: -0.1700

Data Index: 1056555 (C4 (Web Text))

Max Activating Token Index: 569

Text #4

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4944. Min Act: -0.1700

Data Index: 1272483 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4631. Min Act: -0.1700

Data Index: 977407 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4474. Min Act: -0.1700

Data Index: 414958 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4631. Min Act: -0.1700

Data Index: 494683 (C4 (Web Text))

Max Activating Token Index: 322

Text #8

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4317. Min Act: -0.1700

Data Index: 1169584 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.5101. Min Act: -0.1700

Data Index: 889494 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4160. Min Act: -0.1700

Data Index: 649277 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4160. Min Act: -0.1700

Data Index: 401833 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4004. Min Act: -0.1700

Data Index: 1177469 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.3690. Min Act: -0.1700

Data Index: 1231915 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.4004. Min Act: -0.1700

Data Index: 1048337 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.3847. Min Act: -0.1700

Data Index: 506566 (C4 (Web Text))

Max Activating Token Index: 196

Text #16

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.3690. Min Act: -0.1700

Data Index: 914877 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.3376. Min Act: -0.1700

Data Index: 789218 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.3690. Min Act: -0.1700

Data Index: 1219793 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 3.7762. Min Range: -3.7762

Max Act: 3.3533. Min Act: -0.1700

Data Index: 1075909 (C4 (Web Text))

Max Activating Token Index: 178