Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 499 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0546. Min Range: -1.0546

Max Act: 1.0546. Min Act: -0.0001

Data Index: 253926 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8607. Min Act: -0.0001

Data Index: 567220 (C4 (Web Text))

Max Activating Token Index: 578

Text #2

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.9149. Min Act: -0.0001

Data Index: 211911 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8605. Min Act: -0.0001

Data Index: 800289 (C4 (Web Text))

Max Activating Token Index: 919

Text #4

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8481. Min Act: -0.0001

Data Index: 1134427 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8917. Min Act: -0.0001

Data Index: 109766 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8346. Min Act: -0.0001

Data Index: 689740 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8630. Min Act: -0.0001

Data Index: 910443 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7935. Min Act: -0.0001

Data Index: 1090735 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7914. Min Act: -0.0001

Data Index: 80281 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.8122. Min Act: -0.0001

Data Index: 327189 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7789. Min Act: -0.0001

Data Index: 972784 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7824. Min Act: -0.0001

Data Index: 559889 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7694. Min Act: -0.0001

Data Index: 787393 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7477. Min Act: -0.0001

Data Index: 506388 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7556. Min Act: -0.0001

Data Index: 263231 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7167. Min Act: -0.0001

Data Index: 441507 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.6921. Min Act: -0.0001

Data Index: 307524 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7117. Min Act: -0.0001

Data Index: 684851 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 1.0546. Min Range: -1.0546

Max Act: 0.7310. Min Act: -0.0001

Data Index: 886664 (C4 (Web Text))

Max Activating Token Index: 573