Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1639 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.9456. Min Act: -0.1700

Data Index: 290745 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.8318. Min Act: -0.1700

Data Index: 947533 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.8000. Min Act: -0.1700

Data Index: 453890 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7662. Min Act: -0.1700

Data Index: 1266680 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7734. Min Act: -0.1700

Data Index: 114438 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7730. Min Act: -0.1700

Data Index: 423046 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7246. Min Act: -0.1700

Data Index: 543331 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7503. Min Act: -0.1700

Data Index: 765359 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7015. Min Act: -0.1700

Data Index: 927392 (C4 (Web Text))

Max Activating Token Index: 27

Text #9

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.7054. Min Act: -0.1700

Data Index: 168182 (C4 (Web Text))

Max Activating Token Index: 98

Text #10

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6828. Min Act: -0.1700

Data Index: 1065891 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6852. Min Act: -0.1700

Data Index: 1024146 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6904. Min Act: -0.1700

Data Index: 414781 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6949. Min Act: -0.1700

Data Index: 618957 (C4 (Web Text))

Max Activating Token Index: 790

Text #14

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1005102 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6655. Min Act: -0.1700

Data Index: 848247 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6636. Min Act: -0.1700

Data Index: 690371 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6764. Min Act: -0.1700

Data Index: 301696 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6533. Min Act: -0.1700

Data Index: 203897 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 2.9456. Min Range: -2.9456

Max Act: 2.6614. Min Act: -0.1700

Data Index: 40632 (C4 (Web Text))

Max Activating Token Index: 839