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

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

Neuron 844 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.8536. Min Act: -0.1700

Data Index: 97449 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.7910. Min Act: -0.1700

Data Index: 256383 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.8223. Min Act: -0.1700

Data Index: 1283581 (C4 (Web Text))

Max Activating Token Index: 418

Text #3

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.8223. Min Act: -0.1700

Data Index: 641443 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.7597. Min Act: -0.1700

Data Index: 329934 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.7284. Min Act: -0.1700

Data Index: 124927 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.6659. Min Act: -0.1700

Data Index: 690547 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.6345. Min Act: -0.1700

Data Index: 709245 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.6345. Min Act: -0.1700

Data Index: 605565 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.6659. Min Act: -0.1700

Data Index: 469303 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.6032. Min Act: -0.1700

Data Index: 670359 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 397462 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 108613 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 111093 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5406. Min Act: -0.1700

Data Index: 303900 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 207529 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 614028 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 1031699 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5406. Min Act: -0.1700

Data Index: 1211963 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 3.8536. Min Range: -3.8536

Max Act: 3.5719. Min Act: -0.1700

Data Index: 468176 (C4 (Web Text))

Max Activating Token Index: 158