Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4346 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.8360. Min Range: -7.8360

Max Act: 7.7544. Min Act: -0.0000

Data Index: 673509 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 7.8360. Min Range: -7.8360

Max Act: 7.2883. Min Act: -0.0000

Data Index: 1332431 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 7.8360. Min Range: -7.8360

Max Act: 7.8360. Min Act: -0.0000

Data Index: 218537 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 7.8360. Min Range: -7.8360

Max Act: 7.5006. Min Act: -0.0000

Data Index: 4394 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 7.8360. Min Range: -7.8360

Max Act: 7.1827. Min Act: -0.0000

Data Index: 1093625 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.8610. Min Act: -0.0000

Data Index: 1010387 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.8531. Min Act: -0.0000

Data Index: 671965 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.7858. Min Act: -0.0000

Data Index: 1296449 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.6979. Min Act: -0.0000

Data Index: 725244 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.5751. Min Act: -0.0000

Data Index: 409143 (C4 (Web Text))

Max Activating Token Index: 70

Text #10

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.5073. Min Act: -0.0000

Data Index: 618951 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 7.8360. Min Range: -7.8360

Max Act: 6.5174. Min Act: -0.0000

Data Index: 1146069 (C4 (Web Text))

Max Activating Token Index: 538

Text #12

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.9645. Min Act: -0.0000

Data Index: 1126220 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.6920. Min Act: -0.0000

Data Index: 1212724 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.4483. Min Act: -0.0000

Data Index: 777696 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.8083. Min Act: -0.0000

Data Index: 419477 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.5901. Min Act: -0.0000

Data Index: 1037755 (C4 (Web Text))

Max Activating Token Index: 369

Text #17

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.3501. Min Act: -0.0000

Data Index: 715562 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.2182. Min Act: -0.0000

Data Index: 1214594 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 7.8360. Min Range: -7.8360

Max Act: 5.4033. Min Act: -0.0000

Data Index: 127255 (C4 (Web Text))

Max Activating Token Index: 753