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

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

Neuron 549 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5966. Min Act: -0.1699

Data Index: 345566 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5809. Min Act: -0.1699

Data Index: 315597 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5809. Min Act: -0.1699

Data Index: 1173529 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5497. Min Act: -0.1699

Data Index: 1156968 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5341. Min Act: -0.1699

Data Index: 592643 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5341. Min Act: -0.1696

Data Index: 863997 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5184. Min Act: -0.1699

Data Index: 317424 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5341. Min Act: -0.1699

Data Index: 1052948 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5028. Min Act: -0.1699

Data Index: 366685 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5028. Min Act: -0.1699

Data Index: 450346 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5028. Min Act: -0.1699

Data Index: 1144829 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5184. Min Act: -0.1699

Data Index: 1324745 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4872. Min Act: -0.1699

Data Index: 773340 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.5028. Min Act: -0.1699

Data Index: 669788 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4872. Min Act: -0.1699

Data Index: 1161941 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4872. Min Act: -0.1699

Data Index: 405571 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4716. Min Act: -0.1699

Data Index: 1126851 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4716. Min Act: -0.1699

Data Index: 153208 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4872. Min Act: -0.1699

Data Index: 216934 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 8.5966. Min Range: -8.5966

Max Act: 8.4872. Min Act: -0.1699

Data Index: 256390 (C4 (Web Text))

Max Activating Token Index: 472