Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4130 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.2015. Min Act: -0.0000

Data Index: 691700 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1897. Min Act: -0.0000

Data Index: 697540 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1701. Min Act: -0.0000

Data Index: 941261 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1813. Min Act: -0.0000

Data Index: 606999 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1687. Min Act: -0.0000

Data Index: 150476 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1688. Min Act: -0.0000

Data Index: 853834 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1650. Min Act: -0.0000

Data Index: 310770 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1686. Min Act: -0.0000

Data Index: 331951 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1586. Min Act: -0.0000

Data Index: 766108 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1568. Min Act: -0.0000

Data Index: 97478 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1567. Min Act: -0.0000

Data Index: 864170 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1162645 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1533. Min Act: -0.0000

Data Index: 716135 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1496. Min Act: -0.0000

Data Index: 190129 (C4 (Web Text))

Max Activating Token Index: 474

Text #14

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1443. Min Act: -0.0000

Data Index: 509957 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1461. Min Act: -0.0000

Data Index: 818369 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1587. Min Act: -0.0000

Data Index: 297432 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1388. Min Act: -0.0000

Data Index: 1112421 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1545. Min Act: 0.0000

Data Index: 192463 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.2015. Min Range: -0.2015

Max Act: 0.1365. Min Act: -0.0000

Data Index: 835157 (C4 (Web Text))

Max Activating Token Index: 625