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

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

Neuron 2862 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.4095. Min Act: -0.0000

Data Index: 828964 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1131185 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1279803 (C4 (Web Text))

Max Activating Token Index: 203

Text #3

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3682. Min Act: -0.0000

Data Index: 173571 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3478. Min Act: -0.0000

Data Index: 307371 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3559. Min Act: -0.0000

Data Index: 1091047 (C4 (Web Text))

Max Activating Token Index: 530

Text #6

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3519. Min Act: -0.0000

Data Index: 390115 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3235. Min Act: -0.0000

Data Index: 191629 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3186. Min Act: -0.0000

Data Index: 761369 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3019. Min Act: -0.0000

Data Index: 220194 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2997. Min Act: -0.0000

Data Index: 677451 (C4 (Web Text))

Max Activating Token Index: 657

Text #11

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3188. Min Act: -0.0000

Data Index: 832294 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1128400 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3248. Min Act: -0.0000

Data Index: 82565 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3162. Min Act: -0.0000

Data Index: 233497 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3069. Min Act: -0.0000

Data Index: 239569 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3080. Min Act: -0.0000

Data Index: 908334 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3002. Min Act: -0.0000

Data Index: 451788 (C4 (Web Text))

Max Activating Token Index: 689

Text #18

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1132031 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.4095. Min Range: -0.4095

Max Act: 0.3191. Min Act: -0.0000

Data Index: 13588 (C4 (Web Text))

Max Activating Token Index: 813