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

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

Neuron 835 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: 5.8651. Min Range: -5.8651

Max Act: 5.8338. Min Act: -0.1700

Data Index: 996447 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.8651. Min Act: -0.1700

Data Index: 53250 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.8651. Min Act: -0.1700

Data Index: 1158443 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.8651. Min Act: -0.1700

Data Index: 588866 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.7401. Min Act: -0.1700

Data Index: 596762 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.7088. Min Act: -0.1700

Data Index: 1087208 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.6776. Min Act: -0.1700

Data Index: 1047849 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.5838. Min Act: -0.1700

Data Index: 1175492 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.5838. Min Act: -0.1700

Data Index: 948358 (C4 (Web Text))

Max Activating Token Index: 687

Text #9

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4588. Min Act: -0.1700

Data Index: 607126 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4588. Min Act: -0.1700

Data Index: 562338 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4276. Min Act: -0.1700

Data Index: 504431 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4588. Min Act: -0.1700

Data Index: 849158 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4588. Min Act: -0.1700

Data Index: 917252 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4588. Min Act: -0.1700

Data Index: 27389 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4901. Min Act: -0.1700

Data Index: 1283735 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.3963. Min Act: -0.1700

Data Index: 973432 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.4276. Min Act: -0.1700

Data Index: 303041 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.5213. Min Act: -0.1700

Data Index: 1145383 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 5.8651. Min Range: -5.8651

Max Act: 5.2713. Min Act: -0.1700

Data Index: 122585 (C4 (Web Text))

Max Activating Token Index: 432