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

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

Neuron 213 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: 5.7638. Min Range: -5.7638

Max Act: 5.7638. Min Act: -0.1700

Data Index: 703196 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.7325. Min Act: -0.1700

Data Index: 29366 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.7325. Min Act: -0.1700

Data Index: 1256556 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6388. Min Act: -0.1700

Data Index: 172623 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.7013. Min Act: -0.1700

Data Index: 994899 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.7013. Min Act: -0.1700

Data Index: 758542 (C4 (Web Text))

Max Activating Token Index: 432

Text #6

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6700. Min Act: -0.1700

Data Index: 1027031 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6700. Min Act: -0.1700

Data Index: 838570 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6700. Min Act: -0.1700

Data Index: 45049 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5763. Min Act: -0.1700

Data Index: 780367 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5763. Min Act: -0.1700

Data Index: 220526 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5763. Min Act: -0.1700

Data Index: 1011585 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6075. Min Act: -0.1700

Data Index: 1123001 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6075. Min Act: -0.1700

Data Index: 1210022 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6075. Min Act: -0.1700

Data Index: 877053 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5763. Min Act: -0.1700

Data Index: 1089317 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5763. Min Act: -0.1700

Data Index: 738539 (C4 (Web Text))

Max Activating Token Index: 597

Text #17

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.6075. Min Act: -0.1700

Data Index: 1115428 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5763. Min Act: -0.1700

Data Index: 294568 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 5.7638. Min Range: -5.7638

Max Act: 5.5138. Min Act: -0.1700

Data Index: 230354 (C4 (Web Text))

Max Activating Token Index: 803