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

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

Neuron 4427 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1381. Min Range: -2.1381

Max Act: 2.1381. Min Act: -0.0000

Data Index: 673465 (C4 (Web Text))

Max Activating Token Index: 885

Text #1

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.7343. Min Act: -0.0000

Data Index: 377728 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.6842. Min Act: -0.0000

Data Index: 534739 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.8622. Min Act: -0.0000

Data Index: 830669 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.6495. Min Act: -0.0000

Data Index: 349497 (C4 (Web Text))

Max Activating Token Index: 632

Text #5

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.6269. Min Act: -0.0000

Data Index: 156537 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4827. Min Act: -0.0000

Data Index: 467232 (C4 (Web Text))

Max Activating Token Index: 810

Text #7

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.6540. Min Act: -0.0000

Data Index: 754499 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.5474. Min Act: -0.0000

Data Index: 1000547 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.5926. Min Act: -0.0000

Data Index: 25773 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.5630. Min Act: -0.0000

Data Index: 1168314 (C4 (Web Text))

Max Activating Token Index: 323

Text #11

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4668. Min Act: -0.0001

Data Index: 27328 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4520. Min Act: -0.0000

Data Index: 455156 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4621. Min Act: -0.0000

Data Index: 589134 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4490. Min Act: -0.0000

Data Index: 519149 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4493. Min Act: -0.0000

Data Index: 962341 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.5180. Min Act: -0.0000

Data Index: 946891 (C4 (Web Text))

Max Activating Token Index: 885

Text #17

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.5087. Min Act: -0.0000

Data Index: 587787 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.4981. Min Act: -0.0000

Data Index: 400541 (C4 (Web Text))

Max Activating Token Index: 501

Text #19

Max Range: 2.1381. Min Range: -2.1381

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1195730 (C4 (Web Text))

Max Activating Token Index: 724