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

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

Neuron 1292 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: 0.4187. Min Range: -0.4187

Max Act: 0.4187. Min Act: -0.0000

Data Index: 881779 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.4094. Min Act: -0.0000

Data Index: 61445 (C4 (Web Text))

Max Activating Token Index: 785

Text #2

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1235485 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3608. Min Act: -0.0000

Data Index: 456712 (C4 (Web Text))

Max Activating Token Index: 617

Text #4

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3321. Min Act: -0.0000

Data Index: 441634 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2929. Min Act: -0.0000

Data Index: 293519 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2984. Min Act: -0.0000

Data Index: 358702 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.3049. Min Act: -0.0000

Data Index: 570068 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2832. Min Act: -0.0000

Data Index: 205381 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1051444 (C4 (Web Text))

Max Activating Token Index: 976

Text #10

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1068593 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2774. Min Act: -0.0000

Data Index: 518683 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2662. Min Act: -0.0000

Data Index: 428526 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2651. Min Act: -0.0000

Data Index: 520402 (C4 (Web Text))

Max Activating Token Index: 901

Text #14

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2710. Min Act: -0.0000

Data Index: 798914 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2671. Min Act: -0.0000

Data Index: 459711 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2580. Min Act: -0.0000

Data Index: 197007 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2550. Min Act: -0.0000

Data Index: 236931 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2529. Min Act: -0.0000

Data Index: 606292 (C4 (Web Text))

Max Activating Token Index: 927

Text #19

Max Range: 0.4187. Min Range: -0.4187

Max Act: 0.2540. Min Act: -0.0000

Data Index: 682477 (C4 (Web Text))

Max Activating Token Index: 897