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

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

Neuron 2004 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: 4.7899. Min Range: -4.7899

Max Act: 4.7899. Min Act: -0.1614

Data Index: 82239 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.7212. Min Act: -0.1698

Data Index: 1090373 (C4 (Web Text))

Max Activating Token Index: 944

Text #2

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.6259. Min Act: -0.1700

Data Index: 1168413 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.5846. Min Act: -0.1700

Data Index: 1124258 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.5772. Min Act: -0.1642

Data Index: 569580 (C4 (Web Text))

Max Activating Token Index: 788

Text #5

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.5020. Min Act: -0.1688

Data Index: 1341024 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.5016. Min Act: -0.1698

Data Index: 1277771 (C4 (Web Text))

Max Activating Token Index: 979

Text #7

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.5156. Min Act: -0.1699

Data Index: 1254985 (C4 (Web Text))

Max Activating Token Index: 800

Text #8

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4763. Min Act: -0.1696

Data Index: 1258542 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4730. Min Act: -0.1700

Data Index: 752862 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4737. Min Act: -0.1700

Data Index: 233632 (C4 (Web Text))

Max Activating Token Index: 954

Text #11

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4594. Min Act: -0.1700

Data Index: 929331 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4858. Min Act: -0.1445

Data Index: 1173982 (C4 (Web Text))

Max Activating Token Index: 488

Text #13

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4826. Min Act: -0.1700

Data Index: 986366 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4876. Min Act: -0.1700

Data Index: 1199332 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4651. Min Act: -0.1700

Data Index: 1144512 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4732. Min Act: -0.1700

Data Index: 1172038 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4730. Min Act: -0.1700

Data Index: 75229 (C4 (Web Text))

Max Activating Token Index: 1004

Text #18

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4890. Min Act: -0.1700

Data Index: 1062370 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 4.7899. Min Range: -4.7899

Max Act: 4.4711. Min Act: -0.1700

Data Index: 534299 (C4 (Web Text))

Max Activating Token Index: 872