Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3543 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1301. Min Act: -0.0001

Data Index: 705334 (C4 (Web Text))

Max Activating Token Index: 360

Text #1

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1222. Min Act: -0.0001

Data Index: 714884 (C4 (Web Text))

Max Activating Token Index: 550

Text #2

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.1043. Min Act: -0.0001

Data Index: 942332 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0906. Min Act: -0.0001

Data Index: 961624 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0907. Min Act: -0.0001

Data Index: 995436 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0921. Min Act: -0.0001

Data Index: 922886 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0911. Min Act: -0.0001

Data Index: 522080 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0921. Min Act: -0.0001

Data Index: 59998 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1303306 (C4 (Web Text))

Max Activating Token Index: 421

Text #9

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1019385 (C4 (Web Text))

Max Activating Token Index: 453

Text #10

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0832. Min Act: -0.0001

Data Index: 1314800 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0904. Min Act: -0.0001

Data Index: 847298 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0883. Min Act: -0.0001

Data Index: 242131 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0842. Min Act: -0.0001

Data Index: 191534 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0814. Min Act: -0.0001

Data Index: 233483 (C4 (Web Text))

Max Activating Token Index: 380

Text #15

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0812. Min Act: -0.0001

Data Index: 147454 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0811. Min Act: -0.0001

Data Index: 863864 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0813. Min Act: -0.0001

Data Index: 253085 (C4 (Web Text))

Max Activating Token Index: 665

Text #18

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0778. Min Act: -0.0001

Data Index: 1464 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.1301. Min Range: -0.1301

Max Act: 0.0825. Min Act: -0.0001

Data Index: 705645 (C4 (Web Text))

Max Activating Token Index: 902