Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1467 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.8984. Min Act: -0.1700

Data Index: 1500188 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.8359. Min Act: -0.1700

Data Index: 858246 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.8046. Min Act: -0.1700

Data Index: 799494 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 378130 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7733. Min Act: -0.1700

Data Index: 704295 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7733. Min Act: -0.1700

Data Index: 1051603 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7733. Min Act: -0.1700

Data Index: 586009 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 747707 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 682769 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 1052400 (C4 (Web Text))

Max Activating Token Index: 474

Text #10

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 209058 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7107. Min Act: -0.1700

Data Index: 1132601 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7107. Min Act: -0.1700

Data Index: 604521 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7107. Min Act: -0.1700

Data Index: 835935 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7107. Min Act: -0.1700

Data Index: 935262 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 617643 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7420. Min Act: -0.1700

Data Index: 634124 (C4 (Web Text))

Max Activating Token Index: 878

Text #17

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7107. Min Act: -0.1700

Data Index: 949595 (C4 (Web Text))

Max Activating Token Index: 579

Text #18

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.7107. Min Act: -0.1700

Data Index: 1472375 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 3.8984. Min Range: -3.8984

Max Act: 3.6794. Min Act: -0.1700

Data Index: 352656 (C4 (Web Text))

Max Activating Token Index: 41