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

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

Neuron 304 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: 3.6737. Min Range: -3.6737

Max Act: 3.6737. Min Act: -0.1700

Data Index: 681882 (C4 (Web Text))

Max Activating Token Index: 145

Text #1

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5354. Min Act: -0.1700

Data Index: 1304887 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5205. Min Act: -0.1699

Data Index: 582852 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4956. Min Act: -0.1697

Data Index: 1357364 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4882. Min Act: -0.1699

Data Index: 138106 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4798. Min Act: -0.1700

Data Index: 906498 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4653. Min Act: -0.1700

Data Index: 897747 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4780. Min Act: -0.1700

Data Index: 629122 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4821. Min Act: -0.1699

Data Index: 91770 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4645. Min Act: -0.1699

Data Index: 740328 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4688. Min Act: -0.1698

Data Index: 1258967 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4724. Min Act: -0.1590

Data Index: 825386 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4454. Min Act: -0.1653

Data Index: 704139 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4442. Min Act: -0.1700

Data Index: 775244 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4519. Min Act: -0.1699

Data Index: 890416 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4420. Min Act: -0.1696

Data Index: 873881 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4356. Min Act: -0.1698

Data Index: 120569 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4197. Min Act: -0.1700

Data Index: 264596 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4415. Min Act: -0.1700

Data Index: 310225 (C4 (Web Text))

Max Activating Token Index: 942

Text #19

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4113. Min Act: -0.1691

Data Index: 558933 (C4 (Web Text))

Max Activating Token Index: 279